Reminder Information Broadcasting Method, Device, and Electronic Device

Abstract

An embodiment of the present application discloses a method for broadcasting reminder information, belonging to the field of computer technology, which helps to improve the timeliness of broadcasting reminder information. The method for broadcasting reminder information disclosed in the embodiment of the present application includes: obtaining reminder information to be broadcast; selecting at least two pieces of the reminder information to be broadcast as the current reminder information to be broadcast; performing local information fusion processing on the current reminder information to be broadcast to obtain a fused reminder voice; and broadcasting the current reminder information to be broadcast based on the fused reminder voice. The method for broadcasting reminder information disclosed in the embodiment of the present application combines and broadcasts a type of reminder information, thereby accelerating the broadcasting speed of the reminder information, without losing the reminder information, and without the situation of serious lag and interruption of the broadcast information, achieving the effect of efficiently and timely reaching the reminder information to the user.

Description

Technical Field

[0001] Embodiments of the present application relate to the field of computer technologies, and in particular, to a method, apparatus, electronic device, and computer-readable storage medium for playing reminder information. Background Art

[0002] In the prior art, in order to facilitate users to obtain received messages in a timely manner, some communication clients usually play reminder voices of received instant communication messages to users in the form of voice broadcast. Taking the merchant-side client of a food delivery application as an example, during lunch or dinner hours when the number of food delivery orders is particularly large, the merchant-side client is usually in the order processing state and cannot view the information displayed on the client page in a timely manner. By playing reminder voices for received orders to reach the merchant, the merchant can be effectively reminded of the order information that needs to be processed, facilitating the merchant to process food delivery orders in a timely manner.

[0003] In the prior art, there are mainly the following three methods for playing reminder information by voice. First, interruptive broadcast, that is, when playing a reminder voice, if another reminder voice needs to be played, the currently being broadcast reminder voice will be interrupted, and the user can only hear the last reminder voice. Second, ignore broadcast, that is, only one reminder voice can be broadcast at the same time, and reminder voices received during the broadcast of a reminder voice will not be broadcast. Third, sequential broadcast, that is, the received reminder voices are broadcast in sequence.

[0004] It can be seen that the reminder information broadcast methods in the prior art at least have the defect that when multiple reminder messages are received simultaneously or continuously within a short period of time, some reminder messages cannot be broadcast in a timely manner, resulting in the client user not being able to obtain message reminders in a timely manner. Summary of the Invention

[0005] Embodiments of the present application provide a method for playing reminder information, which helps to improve the timeliness of playing reminder information.

[0006] To solve the above problems, in a first aspect, embodiments of the present application provide a method for playing reminder information, including:

[0007] Obtain reminder information to be broadcast;

[0008] Select at least two pieces of the reminder information to be broadcast as the currently broadcast reminder information;

[0009] Perform local information fusion processing on the currently broadcast reminder information to obtain a fused reminder voice;

[0010] Based on the fused reminder voice, broadcast the currently broadcast reminder information.

[0011] Second aspect, an embodiment of the present application provides a reminder information broadcasting device, including:

[0012] A reminder information to be broadcast acquisition module, configured to acquire reminder information to be broadcast;

[0013] A current broadcast reminder information selection module, configured to select at least two pieces of the reminder information to be broadcast as current broadcast reminder information;

[0014] A fusion processing module, configured to perform local information fusion processing on the current broadcast reminder information to obtain a fused reminder voice;

[0015] A reminder broadcast module, configured to broadcast the current broadcast reminder information based on the fused reminder voice.

[0016] Third aspect, an embodiment of the present application further discloses an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, the reminder information broadcasting method described in the embodiments of the present application is implemented.

[0017] Fourth aspect, an embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored. When the program is executed by a processor, the steps of the reminder information broadcasting method disclosed in the embodiments of the present application are implemented.

[0018] The reminder information broadcasting method disclosed in the embodiments of the present application helps to improve the timeliness of broadcasting reminder information by acquiring reminder information to be broadcast, selecting at least two pieces of the reminder information to be broadcast as current broadcast reminder information, then performing local information fusion processing on the current broadcast reminder information to obtain a fused reminder voice, and finally broadcasting the current broadcast reminder information based on the fused reminder voice.

[0019] The above description is only an overview of the technical solution of the present application. In order to be able to understand the technical means of the present application more clearly, it can be implemented according to the content of the specification. And in order to make the above and other purposes, features, and advantages of the present application more obvious and understandable, the specific embodiments of the present application are hereinafter specifically exemplified. Description of the Drawings

[0020] To make the objectives, technical solutions, and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Apparently, the described embodiments are some, but not all, of the embodiments of the present application. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present application without creative efforts shall fall within the protection scope of the present application.

[0021] Figure 1 It is a flowchart of the reminder information broadcasting method according to the first embodiment of the present application;

[0022] Figure 2 It is one of the comparison diagrams of the broadcasting effects of the reminder information broadcasting method according to the first embodiment of the present application;

[0023] Figure 3 It is the second comparison diagram of the broadcasting effects of the reminder information broadcasting method according to the first embodiment of the present application;

[0024] Figure 4 It is a schematic structural diagram of the reminder information broadcasting device according to the second embodiment of the present application;

[0025] Figure 5 Schematically shows a block diagram of an electronic device for executing the method according to the present application; and

[0026] Figure 6 Schematically shows a storage unit for holding or carrying program code for implementing the method according to the present application. Detailed implementation manners

[0027] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

[0028] Embodiment 1

[0029] A reminder information broadcasting method disclosed in an embodiment of the present application, as Figure 1 shown, the method includes: step 110 to step 140.

[0030] Step 110, obtain the reminder information to be broadcast.

[0031] The reminder information to be broadcast described in the embodiment of the present application is generated by an information reminder system.

[0032] In some embodiments of the present application, before obtaining the reminder information to be broadcast, it further includes: receiving an order operation prompt information matching the corresponding order information sent by a preset order management system in response to any one of an order generation operation, an order cancellation operation, an order refund operation, and an order after-sales operation; generating a reminder information to be broadcast of a corresponding category according to the order operation prompt information, and storing it in the reminder information cache queue corresponding to the corresponding category. For example, after the user submits an order, the preset order management system will store the order information submitted by the user and generate a reminder information for generating an order. Then, the reminder information for generating an order will be pushed to the information reminder system. Among them, the order operation prompt information includes information such as the operation type and the order content.

[0033] The information reminder system generates reminder information to be broadcast of a corresponding information category according to the source or content of the received message. Among them, the reminder information of each information category corresponds to a fixed data format. The reminder information of each information category will include numerical information at a specified position. The numerical information is used to indicate the numerical information of the number of messages, or the numerical information that matches the received information content reminded by the current reminder information (for example, the amount of a takeaway order, the amount of a refund order, the number of products in an order, etc.).

[0034] Each reminder information to be broadcast is set with a corresponding information category identifier. For example, when the reminder system generates reminder information according to the received message, it will also set the information category that the reminder information matches. The information categories described in the embodiments of the present application include, but are not limited to, one or more of the following: customer service request reminder information, takeaway order reminder information, ticket order reminder information, refund application reminder information.

[0035] For example, in the scenario of takeaway order message reminder, the reminder system can generate a takeaway order reminder information according to the received order message. The content of the takeaway order reminder information can be "You have 1 new takeaway order, with an expected income of 36 yuan. Please process it in time." Among them, the format of the takeaway order reminder information is: speech text 1 + number of messages + speech text 2 + order amount + speech text 3.

[0036] For another example, in the scenario of ticket reservation order reminder, the reminder system can generate a ticket order reminder information according to the received order message. The content of the ticket order reminder information can be "You have 1 new ticket order, with 3 tickets. Please process it in time." Among them, the format of the ticket order reminder information is: speech text 1 + number of messages + speech text 2 + number of products + speech text 3.

[0037] For another example, in the scenario of customer service message reminder, the reminder system can generate a customer service request reminder message based on the received customer service message. The content of the customer service request reminder message can be "You have 1 customer service message, please handle it in time". Among them, the format of the customer service request reminder message is: speech text 1 + message quantity + speech text 2.

[0038] In some embodiments of the present application, reminder message templates corresponding to each information category can be predefined. Each of the templates will match at least one keyword position information. For the reminder message of each information category, only the content at the position indicated by the corresponding keyword position information is variable, and the content at other positions is the fixed template content. For example, when generating an takeaway order reminder message, by analyzing the currently received message, the order amount associated with the currently received message is determined in real time, and the content at the position specified by the corresponding keyword position information is replaced with the determined order amount, then a takeaway order reminder message can be generated.

[0039] In some embodiments of the present application, the reminder message to be broadcast can be a voice message. For example, the reminder message to be broadcast is stored and transmitted in the form of an audio file. In other embodiments of the present application, the reminder message to be broadcast can be a text message. For example, the reminder message to be broadcast is stored and transmitted in the form of a text string.

[0040] In the prior art, after obtaining the reminder message to be broadcast, the broadcast resource is directly called to broadcast the obtained reminder message to be broadcast; or, after obtaining the reminder message to be broadcast, it is further determined whether the broadcast resource is available. If it is available, the broadcast resource is directly called to broadcast the obtained reminder message to be broadcast; if the broadcast resource is unavailable, the broadcast is abandoned; or, a broadcast queue is set up to cache the obtained reminder messages to be broadcast. After obtaining the reminder message to be broadcast, it is further determined whether the broadcast resource is available. If it is available, the broadcast resource is directly called to broadcast the obtained reminder message to be broadcast. If the broadcast resource is unavailable, the obtained reminder message to be broadcast is sequentially added to the broadcast queue and broadcast in the order of first in first out.

[0041] In some embodiments of the present application, the obtaining of the reminder message to be broadcast includes: obtaining all the reminder messages to be broadcast stored in the preset reminder message to be broadcast cache queue. In some embodiments of the present application, a reminder message to be broadcast cache queue will be preset in advance. After obtaining a reminder message to be broadcast, the obtained reminder message to be broadcast is added to the reminder message to be broadcast cache queue. Then, it is further determined whether the broadcast resource is available. If it is available, multiple reminder messages to be broadcast are selected from the cache queue for combined broadcast.

[0042] In some embodiments of the present application, the to-be-broadcast reminder information can be obtained according to the trigger of the playback synchronization signal. For example, a callback function is set within the playback function. After a reminder voice is broadcast, a PlaySync signal is sent to trigger the broadcast of the next reminder voice.

[0043] Step 120: Select at least two pieces of the to-be-broadcast reminder information as the currently broadcast reminder information.

[0044] If there is only one piece of to-be-broadcast reminder information obtained, the broadcast resource can be directly called for broadcasting.

[0045] If multiple pieces of to-be-broadcast reminder information are obtained, multiple pieces of to-be-broadcast reminder information can be selected from the multiple pieces of to-be-broadcast reminder information for combined broadcast. For example, when the obtained to-be-broadcast reminder information includes 3 takeaway order reminder messages and 1 refund application reminder message, the 3 takeaway order reminder messages can be taken out first for combined broadcast, or the 1 refund application reminder message can be taken out first for broadcast.

[0046] In some embodiments of the present application, the step of selecting at least two pieces of the to-be-broadcast reminder information as the currently broadcast reminder information includes: using all the obtained to-be-broadcast reminder information as the currently broadcast reminder information. When all the obtained to-be-broadcast reminder information belongs to the same category (such as only takeaway order reminder information), or when no category information is set for the to-be-broadcast reminder information, all the to-be-broadcast reminder information in the mixed storage queue can be fused and broadcast.

[0047] In some preferred embodiments of the present application, the to-be-broadcast reminder information is fused and broadcast according to categories. First, determine the category of to-be-broadcast reminder information with the highest broadcast priority among all types of reminder information in the to-be-broadcast reminder information, and then take out the to-be-broadcast reminder information with the highest broadcast priority in this category for combined broadcast.

[0048] In some embodiments of the present application, the step of selecting at least two of the to-be-broadcast reminder messages as the current broadcast reminder messages includes: selecting at least two of the to-be-broadcast reminder messages that match the highest broadcast priority according to the broadcast priority matched by the to-be-broadcast reminder messages. For example, according to the time when each of the to-be-broadcast reminder messages is received, determine the information category of the to-be-broadcast reminder message with the longest time from the reception time to the current time. Then, among all the to-be-broadcast reminder messages obtained, determine the to-be-broadcast reminder messages that match this information category as the to-be-broadcast reminder messages with the highest matched broadcast priority. For another example, the information category with the highest matched broadcast priority can be determined according to the broadcast preference setting. If the user sets to give priority to playing refund application reminder messages, the broadcast priority for playing refund application reminder messages can be set as the highest broadcast priority. Then, determine the to-be-broadcast reminder messages corresponding to the highest broadcast priority as the current broadcast reminder messages.

[0049] In some embodiments of the present application, the broadcast priority matched by the to-be-broadcast reminder messages is determined by the following method: determine the broadcast priorities respectively matched by the to-be-broadcast reminder messages according to one or more factors among the number of each type of reminder message, the time when each of the to-be-broadcast reminder messages is received, the broadcast preference setting, and the message intention matching degree within the time interval. That is, according to one or more factors, and in accordance with a preset calculation strategy, comprehensively determine the broadcast priorities matched by the reminder messages of each information category. Then, determine the highest broadcast priority among the broadcast priorities, and the to-be-broadcast reminder messages matched by the highest broadcast priority.

[0050] In some embodiments of the present application, determining the broadcast priorities respectively matched by the to-be-broadcast reminder messages according to one or more factors among the quantity of each type of reminder message, the time when each to-be-broadcast reminder message is received, the broadcast preference settings, and the message intention matching degree within a time interval includes: respectively determining the single-factor priority scores of each type of reminder message according to the quantity of each type of reminder message, the time when each to-be-broadcast reminder message is received, the broadcast preference settings, and the message intention matching degree within a time interval; performing a weighted operation based on the single-factor priority scores according to a preset factor weight, and determining the broadcast priorities respectively matched by each type of reminder message in the to-be-broadcast reminder messages according to the result of the weighted operation. For example, respectively determining the first broadcast priority score Q1 respectively matched by each type of reminder message in the to-be-broadcast reminder messages according to the quantity of each type of reminder message, respectively determining the second broadcast priority score Q2 respectively matched by each type of reminder message in the to-be-broadcast reminder messages according to the broadcast preference settings, respectively determining the third broadcast priority score Q3 respectively matched by each type of reminder message in the to-be-broadcast reminder messages according to the time when each to-be-broadcast reminder message is received, and then respectively determining the fourth broadcast priority score Q4 respectively matched by each type of reminder message in the to-be-broadcast reminder messages according to the message intention matching degree within a time interval. Finally, for each type of to-be-broadcast reminder message, directly adding the above four broadcast priority scores or performing a weighted sum according to different weights, and using the obtained sum result as the play priority matched by this type of to-be-broadcast reminder message.

[0051] In some embodiments of the present application, when respectively determining the first broadcast priority score Q1 respectively matched by each type of reminder message in the to-be-broadcast reminder messages according to the quantity of each type of reminder message, the first broadcast priority score is positively correlated with the quantity of the to-be-broadcast reminder messages of the corresponding information category, that is, the higher the quantity of the to-be-broadcast reminder messages included in the information category, the higher the first broadcast priority score matched by it, and the lower the quantity of the to-be-broadcast reminder messages included in the information category, the lower the first broadcast priority score matched by it. For example, the proportion of the quantity of each type of to-be-broadcast reminder message in the total to-be-broadcast reminder messages can be used as the first broadcast priority score.

[0052] In some embodiments of the present application, users are allowed to perform weighted sorting on reminder messages of different information categories. When calculating the broadcast priority of reminder messages, the higher the weight of an information category, the higher its broadcast priority. When determining the second broadcast priority score Q2 corresponding to each reminder message of each category in the reminder messages to be broadcast according to the broadcast preference settings, the second broadcast priority score consistent with the weight sorting size can be set for the corresponding information category according to the weighted sorting of reminder messages of various information categories set by the user. For example, if the user sets the weighted sorting of reminder messages for customer service requests, takeout order reminders, ticket order reminders, and refund application reminders from high to low as: refund application reminders, customer service request reminders, takeout order reminders, ticket order reminders, then the second broadcast priority scores of the reminder messages of the above information categories can be 4, 3, 2, and 1 in sequence.

[0053] In some embodiments of the present application, the longer the reception time of a certain reminder message to be broadcast is from the current time, the higher the broadcast priority of this message. When determining the third broadcast priority score Q3 corresponding to each reminder message of each category in the reminder messages to be broadcast according to the reception time of each received reminder message, the average duration of the reception time of the reminder messages to be broadcast in each information category from the current time can be determined, and according to the strategy positively correlated with the average duration, the third broadcast priority score corresponding to the reminder messages to be broadcast in the corresponding information category can be determined.

[0054] In some embodiments of the present application, the user receiving the reminder message can dynamically adjust the broadcast priority of reminder messages of different information categories according to the sending time (which is also the reception time) of the reminder message. When determining the fourth broadcast priority score Q4 corresponding to each reminder message of each category in the reminder messages to be broadcast according to the message intention matching degree within the time interval, the fourth broadcast priority score corresponding to each reminder message of each category in the reminder messages to be broadcast can be determined according to the broadcast priority score increase value matched by the preset time interval. For example, the user receiving the reminder message can preset to increase the broadcast priority of takeout order reminder messages during the lunch peak and dinner peak time intervals of takeout orders (such as the time intervals from 11:00 to 13:00 and from 17:00 to 19:00), determine the broadcast priority score increase value of takeout order reminder messages to be 5, while the broadcast priority score increase value of reminder messages to be broadcast in other information categories is 0, then the broadcast priority score increase value can be determined as the fourth broadcast priority score of the reminder messages to be broadcast in the corresponding information category.

[0055] In some embodiments of the present application, since the above four broadcast priority scores are obtained through different strategies and their score values are based on different dimensions, in order to further improve the accuracy of calculating the broadcast priority, the first broadcast priority score, the second broadcast priority score, the third broadcast priority score, and the fourth broadcast priority score may first be normalized. Then, based on the normalized first broadcast priority score, second broadcast priority score, third broadcast priority score, and fourth broadcast priority score, the broadcast priority of the reminder information to be broadcast for each type of information is further calculated.

[0056] Step 130: Perform local information fusion processing on the current broadcast reminder information to obtain a fused reminder voice.

[0057] Since the determined current broadcast reminder information belongs to the same information category and has the same format data, the key information to be fused can be extracted by continuing to parse and process the current broadcast reminder information, and the key information is fused to generate a new reminder information.

[0058] In some embodiments of the present application, the performing local information fusion processing on the current broadcast reminder information to obtain a fused reminder voice includes: performing content fusion processing on the information content corresponding to the keyword position information in the current broadcast reminder information according to the keyword position information matched by the current broadcast reminder information to obtain a fused reminder voice. For example, for a takeaway order reminder information, its format is: speech text 1 + number of messages + speech text 2 + order amount + speech text 3. Then, the value of the number of messages in a takeaway order reminder information can be determined according to the keyword position information indicating "number of messages" in the takeaway order reminder information, and the value of the order amount in this takeaway order reminder information can be determined according to the keyword position information indicating "order amount". After determining the value of the number of messages and the value of the order amount in each takeaway order reminder information obtained according to the above method, the values of the number of messages are summed to obtain the total number of messages, and the values of the order amount are summed to obtain the total order amount. Then, the total number of messages and the total order amount are respectively substituted for the number of messages and the order amount in a obtained takeaway order reminder information, that is, a fused takeaway order reminder information is obtained.

[0059] In some embodiments of the present application, the current broadcast reminder information is audio information. The content fusion process is performed on the information content corresponding to the keyword position information in the current broadcast reminder information according to the keyword position information matched with the current broadcast reminder information, to obtain a fused reminder voice, including: obtaining at least one key voice position information matched with the current broadcast reminder information; determining the key voice segments respectively matched with each key voice position information in each current broadcast reminder information; for each key voice position information, performing content fusion processing on the key voice segments matched with the key voice position information according to the aggregation algorithm corresponding to the key voice position information, to obtain a content fusion result matched with each key voice position information; and fusing the content fusion result with the audio information other than the key voice segments in the current broadcast reminder information, to obtain a fused reminder voice.

[0060] In some embodiments of the present application, the reminder information to be broadcast is audio information, which is stored and transmitted in the form of an audio file. That is, the current broadcast reminder information is audio information, which is stored in the form of an audio file. In some embodiments of the present application, each information category has a fixed information format. Therefore, in the audio file of the reminder information of each information category, the start timestamp and end timestamp of the voice segments corresponding to different data fields are basically the same. In view of this, in some embodiments of the present application, the broadcast client will pre-download the audio file feature data of each category of information, such as stored as a position-map file, for describing the key voice position information in the audio file of this category of information, that is, the start timestamp and end timestamp of the voice segments that need to be fused in the audio file of this category of information. Taking the takeaway order reminder information "You have 1 new takeaway order, with an estimated income of 36 yuan. Please process it in time" as an example, the audio file feature data thereof includes two key voice position information, which are respectively the start timestamp and end timestamp of the voice segment of the message quantity "1" (such as 1.22 seconds and 1.55 seconds), and the start timestamp and end timestamp of the voice segment of the order amount "36" (such as 15.10 seconds and 16.20 seconds). According to this method, the message quantity voice segment and the order amount voice segment in each current broadcast reminder information are respectively determined.

[0061] In some embodiments of the present application, the reminder information to be broadcast of different information categories can be stored in different arrays. When receiving a reminder information to be broadcast of a certain information category, the broadcast client simultaneously loads the audio file feature data corresponding to the reminder information to be broadcast of this information category into the memory. To save content space, the audio file feature data corresponding to the reminder information to be broadcast of each category can be loaded only once.

[0062] In some embodiments of the present application, performing content fusion processing on the key voice segments matching the key voice position information according to the aggregation algorithm corresponding to the key voice position information to obtain a content fusion result matching each key voice position information includes: identifying the information value corresponding to the key voice segment matching the key voice position information in each current broadcast reminder message; performing content fusion processing on the information value according to the aggregation algorithm corresponding to the key voice position information to obtain a fused information value; and converting the fused information value into a fused voice through a preset text-to-speech engine to obtain a content fusion result matching each key voice position information. After determining the key voice segments matching the key voice position information in each current broadcast reminder message, respectively intercepting these two voice segments in each current broadcast reminder message and performing identification to determine the message quantity value and order amount value corresponding to these two voice segments in each current broadcast reminder message. Next, adding up the message quantity values in all the current broadcast reminder messages to obtain the total message quantity; adding up the order amount values in all the current broadcast reminder messages to obtain the total order amount. Then, converting the obtained total message quantity and total order amount into fused voices respectively through a preset text-to-speech engine to obtain a content fusion result matching the message quantity voice segment and a content fusion result matching the order amount voice segment.

[0063] In some embodiments of the present application, fusing the content fusion result with the audio information other than the key voice segment in the current broadcast reminder message to obtain a fused reminder voice includes: replacing the key voice segment matching the corresponding key voice position information in a current broadcast reminder message with the content fusion result to obtain a fused reminder voice. For example, when the content formats of the current broadcast reminder messages are the same, replacing the message quantity voice segment (such as the voice segment between 1.22 seconds and 1.55 seconds) in an outer meal order reminder message with the content fusion result matching the message quantity voice segment (i.e., the voice of the total message quantity), and replacing the order amount voice segment (such as the voice segment between 15.10 seconds and 16.20 seconds) in this outer meal order reminder message with the content fusion result matching the order amount voice segment (i.e., the voice of the total order amount) to obtain a fused reminder voice, that is, the outer meal order reminder message after fusion processing.

[0064] Taking the current broadcast reminder message including 3 takeaway order reminder messages as an example, assume the 3 takeaway order reminder messages are respectively: "You have 1 new takeaway order with an expected income of 36 yuan. Please handle it in time.", "You have 1 new takeaway order with an expected income of 15 yuan. Please handle it in time.", "You have 1 new takeaway order with an expected income of 24 yuan. Please handle it in time." After fusion processing, the obtained takeaway order reminder message is: "You have 3 new takeaway orders with an expected income of 75 yuan. Please handle it in time."

[0065] In some embodiments of the present application, after determining the key speech segment position information in the current broadcast reminder message, one of the current broadcast reminder messages can be cut according to the key speech segment position information, and it is cut into a speech segment sequence composed of a plurality of sequentially connected speech segments. After obtaining the content fusion result corresponding to each key speech segment position information, the corresponding speech segment in the speech segment sequence is replaced by the content fusion result corresponding to each key speech segment position information, and then, the replaced speech segment sequence is sequentially synthesized into a fused reminder voice.

[0066] In other embodiments of the present application, fusing the content fusion result with the audio information other than the key speech segment in the current broadcast reminder message to obtain a fused reminder voice, including: extracting semantic information from the audio information other than the key speech segment in each current broadcast reminder message to generate an audio information template; splicing the content fusion result to the corresponding position in the information template to obtain a fused reminder voice. For example, for a type of reminder message to be broadcast, a fused audio information template is preset. When selecting a type of reminder message to be broadcast as the current broadcast reminder message for broadcasting, after determining the content fusion result, the content fusion result can be spliced to the corresponding audio file position according to the format of the audio information template set for this type of reminder message to be broadcast. When the content formats are different, a fused reminder voice is obtained.

[0067] In some embodiments of the present application, the local information fusion processing of the current broadcast reminder information to obtain a fused reminder voice includes: respectively determining the first information and the second information in each piece of the current broadcast reminder information through semantic recognition of the current broadcast reminder information; wherein, the first information is numerical information, and the second information is descriptive information; cumulatively processing the first information to obtain first fused information; and, performing semantic recognition on the second information based on a preset language processing model to obtain third information; obtaining first fused information according to the first fused information and the third information. Among them, for the specific implementation manners of respectively determining the first information and the second information in each piece of the current broadcast reminder information through semantic recognition of the current broadcast reminder information, reference can be made to the prior art and will not be elaborated in the embodiments of the present application. The third information is preset descriptive information, and for the specific implementation manners of performing semantic recognition on the second information based on a preset language processing model to obtain the third information, reference can be made to the prior art and will not be elaborated in the embodiments of the present application. When obtaining the first fused information according to the first fused information and the third information, the first fused information and the third information can be spliced and processed according to the format of the third information.

[0068] Step 140, based on the fused reminder voice, broadcast the current broadcast reminder information.

[0069] After the fused reminder voice that fuses the key information of multiple pieces of the current broadcast reminder information is obtained after the fusion processing of the current broadcast reminder information, the fused reminder voice is broadcast by calling a broadcast resource (such as the audio playback interface of the client system).

[0070] The reminder information broadcast method disclosed in the embodiments of the present application, by obtaining the reminder information to be broadcast, selecting at least two pieces of the reminder information to be broadcast as the current broadcast reminder information, then performing local information fusion processing on the current broadcast reminder information to obtain a fused reminder voice, and finally, based on the fused reminder voice, broadcasting the current broadcast reminder information, helps to improve the timeliness of the broadcast of the reminder information.

[0071] Taking the example that the broadcast client continuously receives the above-mentioned 3 takeaway order reminder messages "You have 1 takeaway order, please process it in time" within 3 seconds, if the broadcast duration of each takeaway order reminder message is 5 seconds, such as Figure 2As shown, when using the sequential broadcast method in the prior art, it takes about 15 seconds to broadcast 3 takeout order reminder messages; when using the interruptive broadcast method, the broadcast duration of the above 3 messages is 7 seconds, but the first two takeout order reminder messages cannot be fully broadcast, and the user can only hear the reminder message that there is 1 takeout order to be processed completely; when using the ignore broadcast method, the broadcast duration is 5 seconds, but the last two takeout order reminder messages cannot be broadcast, and the user can only hear the reminder message that there is 1 takeout order to be processed. When using the reminder voice broadcast method disclosed in the embodiments of the present application, it takes about 5 seconds to broadcast 3 takeout order reminder messages, and the user can hear the reminder messages that there are 3 takeout orders to be processed. It can be seen that the reminder message broadcast method disclosed in the embodiments of the present application combines a type of reminder messages for combined broadcast, which speeds up the broadcast speed of reminder messages, does not lose reminder messages, and does not have the situation of serious lag and interruption of broadcast messages, achieving the effect of efficiently and timely reaching the reminder messages to users.

[0072] On the other hand, by combining multiple factors to determine the broadcast priority of reminder messages and preferentially broadcasting the reminder messages of messages with higher processing time requirements, it can assist users in improving the response speed of important messages and improving the user experience. Taking the example that 1 takeout order reminder message, 1 refund application reminder message, and 1 takeout order reminder message are continuously received 1 second after the broadcast client starts to broadcast a takeout order reminder message, if the broadcast duration of each reminder message is 5 seconds, as Figure 3 shown, when using the sequential broadcast method in the prior art, it takes 8 seconds after receiving this message to broadcast the refund application reminder message; when using the interruptive broadcast method or the ignore broadcast method, the refund application reminder message cannot be fully broadcast. When using the reminder voice broadcast method disclosed in the embodiments of the present application, the message will be fully broadcast 3 seconds after receiving the refund application reminder message. It can be seen that the reminder message broadcast method disclosed in the embodiments of the present application combines the priorities of reminder messages to perform sequential combined broadcast on the received reminder messages, which helps users obtain the reminder messages of important messages in a timely manner and improves the user experience. In the customer service application, through the reminder voice broadcast method disclosed in the embodiments of the present application, the reminder voice with a higher priority set by the user is preferentially broadcast, so that the user can obtain the feedback of important problems in a timely manner and process them in a timely manner, which can effectively reduce the number of customer complaints.

[0073] Furthermore, users can set the broadcast priorities or weights of different types of reminder messages according to the reminder message broadcast requirements of specific application scenarios to meet the personalized needs of different reminder message broadcast scenarios.

[0074] Embodiment 2

[0075] A reminder message broadcast device disclosed in the embodiments of the present application, as Figure 4As shown, the device includes:

[0076] A reminder message acquisition module 410 to be broadcast, configured to acquire a reminder message to be broadcast;

[0077] A current broadcast reminder message selection module 420, configured to select at least two of the reminder messages to be broadcast as current broadcast reminder messages;

[0078] A fusion processing module 430, configured to perform local information fusion processing on the current broadcast reminder messages to obtain a fused reminder voice;

[0079] A reminder broadcast module 440, configured to broadcast the current broadcast reminder messages based on the fused reminder voice.

[0080] In some embodiments of the present application, the fusion processing module 430 is further configured to:

[0081] According to the keyword position information matched by the current broadcast reminder messages, perform content fusion processing on the information content corresponding to the keyword position information in the current broadcast reminder messages to obtain a fused reminder voice.

[0082] In some embodiments of the present application, the current broadcast reminder messages are audio messages. The performing content fusion processing on the information content corresponding to the keyword position information in the current broadcast reminder messages according to the keyword position information matched by the current broadcast reminder messages to obtain a fused reminder voice includes:

[0083] Obtain at least one key voice position information matched by the current broadcast reminder messages;

[0084] Determine the key voice segments in each of the current broadcast reminder messages that respectively match each of the key voice position information;

[0085] For each of the key voice position information, perform content fusion processing on the key voice segments matched by the key voice position information according to the aggregation algorithm corresponding to the key voice position information to obtain a content fusion result matched by each of the key voice position information;

[0086] Fuse the content fusion result with the audio information other than the key voice segments in the current broadcast reminder messages to obtain a fused reminder voice.

[0087] In some other embodiments of the present application, the fusion processing module 430 is further configured to:

[0088] By performing semantic recognition on the current broadcast reminder information, the first information and the second information in each piece of the current broadcast reminder information are respectively determined; wherein, the first information is numerical information and the second information is descriptive information.

[0089] Cumulatively process the first information to obtain first fusion information; and, perform semantic recognition on the second information based on a preset language processing model to obtain third information.

[0090] Obtain first fusion information according to the first fusion information and the third information.

[0091] In some other embodiments of the present application, the key voice position information includes a key voice start position timestamp and an end position timestamp. The step of performing content fusion processing on the key voice segments matched with the key voice position information according to the aggregation algorithm corresponding to the key voice position information to obtain a content fusion result matched with each key voice position information includes:

[0092] Identify the information values corresponding to the key voice segments matched with the key voice position information in each piece of the current broadcast reminder information.

[0093] Perform content fusion processing on the information values according to the aggregation algorithm corresponding to the key voice position information to obtain fusion information values.

[0094] Convert the fusion information values into fusion voices through a preset text-to-speech engine to obtain a content fusion result matched with each key voice position information.

[0095] In some embodiments of the present application, the current broadcast reminder information selection module 420 is further configured to:

[0096] Use all the to-be-broadcast reminder information obtained as the current broadcast reminder information; or,

[0097] Select at least two pieces of the to-be-broadcast reminder information with the highest matching broadcast priority as the current broadcast reminder information according to the broadcast priority matched with the to-be-broadcast reminder information.

[0098] In some embodiments of the present application, the broadcast priority matched with the to-be-broadcast reminder information is determined by the following method:

[0099] Determine the broadcast priorities respectively matched with the to-be-broadcast reminder information according to one or more factors such as the quantity of each type of reminder information, the time when each piece of the to-be-broadcast reminder information is received, the broadcast preference setting, and the message intention matching degree within the time interval.

[0100] In some embodiments of the present application, the step of determining the broadcast priorities respectively matched by the to-be-broadcast reminder information according to one or more factors among the quantity of each type of reminder information, the time when each piece of the to-be-broadcast reminder information is received, the broadcast preference setting, and the message intention matching degree within a time interval includes:

[0101] Respectively determine the single-factor priority scores of each type of reminder information according to the quantity of each type of reminder information, the time when each piece of the to-be-broadcast reminder information is received, the broadcast preference setting, and the message intention matching degree within a time interval;

[0102] Perform a weighted operation based on the single-factor priority scores according to a preset factor weight, and determine the broadcast priorities respectively matched by each type of reminder information in the to-be-broadcast reminder information according to the result of the weighted operation.

[0103] In some embodiments of the present application, the to-be-broadcast reminder information acquisition module 410 is further configured to:

[0104] Acquire all the to-be-broadcast reminder information stored in the preset to-be-broadcast reminder information cache queue.

[0105] In some embodiments of the present application, the device further includes: a to-be-broadcast reminder information storage module (not shown in the figure),

[0106] The to-be-broadcast reminder information storage module is configured to receive the order operation prompt information matching the corresponding order information sent by the preset order management system in response to any one of an order generation operation, an order cancellation operation, an order refund operation, and an order after-sales operation; and,

[0107] Generate the to-be-broadcast reminder information of the corresponding category according to the order operation prompt information, and store it in the to-be-broadcast reminder information cache queue corresponding to the corresponding category.

[0108] The reminder information broadcast device disclosed in the embodiments of the present application is used to implement the reminder information broadcast method described in Embodiment 1 of the present application. The specific implementation manners of the modules of the device will not be elaborated here, and reference may be made to the specific implementation manners of the corresponding steps in the method embodiments.

[0109] The reminder information broadcast device disclosed in the embodiments of the present application helps to improve the broadcast timeliness of reminder information by acquiring the to-be-broadcast reminder information, selecting at least two pieces of the to-be-broadcast reminder information as the current broadcast reminder information, then performing local information fusion processing on the current broadcast reminder information to obtain a fused reminder voice, and finally broadcasting the current broadcast reminder information based on the fused reminder voice.

[0110] The reminder information broadcast device disclosed in the embodiments of the present application combines and broadcasts a certain type of reminder information, which speeds up the broadcast speed of reminder information, does not lose reminder information, and does not suffer from serious lag or interruption in the broadcast information, achieving the effect of efficiently and timely reaching users with reminder information.

[0111] On the other hand, by combining multiple factors to determine the broadcast priority of reminder information and preferentially broadcasting reminder information for messages with higher processing time requirements, it can assist users in improving the response speed to important messages and enhancing the user experience. For example, 1 second after the broadcast client starts broadcasting a reminder message for a takeout order, it continuously receives 1 reminder message for a takeout order, 1 reminder message for a refund application, and 1 reminder message for a takeout order. If the broadcast duration of each reminder message is 5 seconds, as Figure 3 shown, using the sequential broadcast in the prior art, the reminder message for the refund application needs to be broadcast 8 seconds after receiving this message; using the interruptive broadcast or the ignoring broadcast, the reminder message for the refund application will not be completely broadcast. However, using the reminder voice broadcast device disclosed in the embodiments of the present application, this message will be completely broadcast 3 seconds after receiving the reminder message for the refund application. It can be seen that the reminder information broadcast device disclosed in the embodiments of the present application combines the priorities of reminder information to perform sequential combined broadcasts on the received reminder information, which helps users obtain reminder information for important messages in a timely manner and enhances the user experience. In customer service applications, through the reminder voice broadcast method disclosed in the embodiments of the present application, the reminder voice with a higher priority set by the user is preferentially broadcast, enabling the user to obtain feedback on important issues in a timely manner and thus process them in a timely manner, which can effectively reduce the number of customer complaints.

[0112] Furthermore, users can set the broadcast priorities or weights of different types of reminder information according to the reminder information broadcast requirements in specific application scenarios to meet the personalized needs of different reminder information broadcast scenarios.

[0113] Each embodiment in this specification is described in a progressive manner. The key point of each embodiment is the difference from other embodiments. The same or similar parts among the embodiments can be referred to each other. For the device embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiments.

[0114] The above has provided a detailed introduction to a method and device for broadcasting reminder information. In this article, specific examples are used to elaborate on the principle and implementation manner of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea; at the same time, for those of ordinary skill in the art, according to the idea of the present application, there will be changes in the specific implementation manner and application scope. In summary, the content of this specification should not be construed as a limitation to the present application.

[0115] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art can understand and implement it without creative labor.

[0116] The various component embodiments of the present application can be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art should understand that a microprocessor or a digital signal processor (DSP) can be used in practice to implement some or all of the functions of some or all of the components in the electronic device according to the embodiments of the present application. The present application can also be implemented as a device or device program (such as a computer program and a computer program product) for executing part or all of the methods described herein. Such a program for implementing the present application can be stored on a computer-readable medium, or can be in the form of one or more signals. Such signals can be downloaded from an Internet website, or provided on a carrier signal, or provided in any other form.

[0117] For example, Figure 5An electronic device that can implement the method according to the present application is shown. The electronic device may be a PC, a mobile terminal, a personal digital assistant, a tablet computer, etc. Traditionally, the electronic device includes a processor 510, a memory 520, and program code 530 stored on the memory 520 and executable on the processor 510. When the processor 510 executes the program code 530, the method described in the above embodiments is implemented. The memory 520 may be a computer program product or a computer-readable medium. The memory 520 may be an electronic memory such as a flash memory, an EEPROM (electrically erasable programmable read-only memory), an EPROM, a hard disk, or a ROM. The memory 520 has a storage space 5201 for the program code 530 of a computer program for executing any method step in the above method. For example, the storage space 5201 for the program code 530 may include respective computer programs for implementing various steps in the above method. The program code 530 is computer-readable code. These computer programs may be read from or written into one or more computer program products. These computer program products include program code carriers such as hard disks, compact discs (CDs), memory cards, or floppy disks. The computer program includes computer-readable code, which, when running on the electronic device, causes the electronic device to execute the method according to the above embodiments.

[0118] An embodiment of the present application also discloses a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the steps of the reminder information broadcast method described in Embodiment 1 of the present application are implemented.

[0119] Such a computer program product may be a computer-readable storage medium, and the computer-readable storage medium may have storage segments, storage spaces, etc. arranged similarly to the memory 520 in the Figure 5 shown electronic device. The program code may be stored in the computer-readable storage medium in a suitably compressed form, for example. The computer-readable storage medium is generally a portable or fixed storage unit as described in Figure 6 reference. Generally, the storage unit includes computer-readable code 530', which is code read by the processor, and when these codes are executed by the processor, the respective steps in the method described above are implemented.

[0120] As used herein, the terms "one embodiment", "embodiment", or "one or more embodiments" mean that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the present application. In addition, note that the examples of the phrase "in one embodiment" herein do not necessarily all refer to the same embodiment.

[0121] In the description provided herein, numerous specific details are set forth. However, it will be understood that embodiments of the present application may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail so as not to obscure the understanding of this description.

[0122] In a claim, any reference sign placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The present application may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In a unit claim enumerating several means, several of these means may be embodied by one and the same item of hardware. The use of the words first, second, and third, etc. does not denote any order. These words may be interpreted as names.

[0123] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application and are not intended to limit them. Although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features. These modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the various embodiments of the present application.

Claims

1. A method for broadcasting reminder information, characterized in that, it includes: Obtaining the reminder information to be broadcast; Selecting at least two pieces of the reminder information to be broadcast as the current broadcast reminder information; Performing local information fusion processing on the current broadcast reminder information to obtain a fused reminder voice; Based on the fused reminder voice, broadcasting the current broadcast reminder information; The step of performing local information fusion processing on the current broadcast reminder information to obtain a fused reminder voice includes: According to the keyword position information matched by the current broadcast reminder information, performing content fusion processing on the information content corresponding to the keyword position information in the current broadcast reminder information to obtain a fused reminder voice; When the current broadcast reminder information is audio information, the step of performing content fusion processing on the information content corresponding to the keyword position information in the current broadcast reminder information according to the keyword position information matched by the current broadcast reminder information to obtain a fused reminder voice includes: Obtaining at least one key voice position information matched by the current broadcast reminder information; Determining the key voice segments in each piece of the current broadcast reminder information that respectively match each key voice position information; For each key voice position information, performing content fusion processing on the key voice segments matched by the key voice position information according to the aggregation algorithm corresponding to the key voice position information to obtain a content fusion result matched by each key voice position information; Fusing the content fusion result with the audio information other than the key voice segments in the current broadcast reminder information to obtain a fused reminder voice; The key voice position information includes a key voice start position timestamp and an end position timestamp, and the step of performing content fusion processing on the key voice segments matched by the key voice position information according to the aggregation algorithm corresponding to the key voice position information to obtain a content fusion result matched by each key voice position information includes: Identifying the information value corresponding to the key voice segment matched by the key voice position information in each piece of the current broadcast reminder information; Performing content fusion processing on the information value according to the aggregation algorithm corresponding to the key voice position information to obtain a fused information value; Converting the fused information value into a fused voice through a preset text-to-speech engine to obtain a content fusion result matched by each key voice position information.

2. The method according to claim 1, characterized in that, the step of selecting at least two pieces of the reminder information to be broadcast as the current broadcast reminder information includes: Taking all the obtained reminder information to be broadcast as the current broadcast reminder information; or, Selecting at least two pieces of the reminder information to be broadcast with the highest broadcast priority according to the broadcast priority matched by the reminder information to be broadcast as the current broadcast reminder information.

3. The method according to claim 2, characterized in that, the broadcast priority matched by the reminder information to be broadcast is determined by the following method: Determine the broadcast priorities respectively matched by the to-be-broadcast reminder messages based on one or more factors among the quantity of each type of reminder message, the time when each of the to-be-broadcast reminder messages is received, the broadcast preference settings, and the message intention matching degree within a time interval.

4. The method according to claim 3, wherein, the step of determining the broadcast priorities respectively matched by the to-be-broadcast reminder messages based on one or more factors among the quantity of each type of reminder message, the time when each of the to-be-broadcast reminder messages is received, the broadcast preference settings, and the message intention matching degree within a time interval includes: Determine the single-factor priority scores of each type of reminder message respectively according to the quantity of each type of reminder message, the time when each of the to-be-broadcast reminder messages is received, the broadcast preference settings, and the message intention matching degree within a time interval; Perform a weighted operation based on the single-factor priority scores according to a preset factor weight, and determine the broadcast priorities respectively matched by each type of reminder message in the to-be-broadcast reminder messages according to the result of the weighted operation.

5. The method according to claim 1, wherein, the step of obtaining the to-be-broadcast reminder messages includes: Obtain all the to-be-broadcast reminder messages stored in a preset to-be-broadcast reminder message cache queue.

6. The method according to claim 1, wherein, before the step of obtaining the to-be-broadcast reminder messages, further includes: Receive an order operation prompt message matching the corresponding order information sent by a preset order management system in response to any one of an order generation operation, an order cancellation operation, an order refund operation, and an order after-sales operation; Generate corresponding types of to-be-broadcast reminder messages according to the order operation prompt message, and store them in the to-be-broadcast reminder message cache queue corresponding to the corresponding type.

7. A reminder message broadcast device, wherein, includes: A to-be-broadcast reminder message acquisition module, configured to acquire to-be-broadcast reminder messages; A current broadcast reminder message selection module, configured to select at least two of the to-be-broadcast reminder messages as the current broadcast reminder messages; A fusion processing module, configured to perform local information fusion processing on the current broadcast reminder messages to obtain a fused reminder voice, including: Perform content fusion processing on the information content corresponding to the keyword position information in the current broadcast reminder messages according to the keyword position information matched by the current broadcast reminder messages, to obtain a fused reminder voice; When the current broadcast reminder message is an audio message, the step of performing content fusion processing on the information content corresponding to the keyword position information in the current broadcast reminder messages according to the keyword position information matched by the current broadcast reminder messages to obtain a fused reminder voice includes: Obtain at least one key voice position information matched by the current broadcast reminder message; Determine the key voice segments in each of the current broadcast reminder messages respectively matched with each of the key voice position information; For each of the key voice position information, perform content fusion processing on the key voice segments matching the key voice position information according to the aggregation algorithm corresponding to the key voice position information, to obtain a content fusion result matching each of the key voice position information; Fuse the content fusion result with the audio information other than the key voice segments in the current broadcast reminder information, to obtain a fused reminder voice; The key voice position information includes a key voice start position timestamp and an end position timestamp. The step of performing content fusion processing on the key voice segments matching the key voice position information according to the aggregation algorithm corresponding to the key voice position information, to obtain a content fusion result matching each of the key voice position information, includes: Identify the information value corresponding to the key voice segment matching the key voice position information in each of the current broadcast reminder information; Perform content fusion processing on the information value according to the aggregation algorithm corresponding to the key voice position information, to obtain a fused information value; Through a preset text-to-speech engine, convert the fused information value into a fused voice, to obtain a content fusion result matching each of the key voice position information; A reminder broadcast module, configured to broadcast the current broadcast reminder information based on the fused reminder voice.

8. An electronic device, including a memory, a processor, and program code stored on the memory and executable on the processor, wherein, when the processor executes the program code, the reminder information broadcast method according to any one of claims 1 to 6 is implemented.

9. A computer-readable storage medium, on which program code is stored, wherein, when the program code is executed by a processor, the steps of the reminder information broadcast method according to any one of claims 1 to 6 are implemented.

Images