Intelligent reminding method and device based on speech synthesis and electronic equipment

Abstract

The embodiment of the invention discloses an intelligent reminding method and device based on speech synthesis and electronic equipment. The method comprises the following steps: when a processing instruction is received, determining a target task with the highest sequence in an unprocessed task queue, and generating first voice data; initiating a call request to a target terminal corresponding to the target task, and playing the first voice data after a call channel is established; continuously acquiring second voice data of the target terminal, determining target text data corresponding to the second voice data, and displaying and updating the display text data on the target interface in real time; and receiving and responding to a selection instruction for the candidate reply text, determining a target candidate reply text, and playing the third voice data. According to the embodiment of the invention, the customer service staff can control the server to process a plurality of call tasks at the same time, thereby greatly improving the call reminding efficiency, and guaranteeing that each call reminding task can be processed in time.

Description

Technical Field

[0001] One or more embodiments of the present specification relate to speech synthesis technology, and more particularly to a method, device and electronic device for intelligent reminder based on speech synthesis. Background Art

[0002] With the development of the Internet, users can sign terms, treaties, contracts, etc. with the platform on various platforms. When the contract performance date arrives and the user has not completed the part that needs to be performed in the contract, the platform's customer service staff needs to communicate with the user by phone to remind the user to perform the contract in a timely manner. However, with the growth of platform users, the number of daily telephone reminder tasks for each customer service staff has exceeded 200. Simply relying on customer service staff to make manual telephone reminders can no longer cover all tasks, resulting in untimely reminders for some tasks. Summary of the invention

[0003] In order to solve the above problems, one or more embodiments of this specification describe an intelligent reminder method, device and electronic device based on speech synthesis.

[0004] According to a first aspect, a method for intelligent reminder based on speech synthesis is provided, the method comprising: When receiving a processing instruction, responding to the processing instruction, determining the target task with the highest ranking in the unprocessed task queue, and generating first voice data based on a text reminder template corresponding to the target task; Initiating a call request to a target terminal corresponding to the target task, and playing the first voice data after a call channel is established; Continuously acquiring second voice data of the target terminal, determining target text data corresponding to the second voice data based on a preset natural language processing model, and displaying and updating display text data in real time on a target interface, wherein the display text data includes the target text data and candidate reply texts corresponding to the target text data, wherein the candidate reply texts are determined based on key fields of the target text data; Receive and respond to a selection instruction for the candidate reply text, determine a target candidate reply text, and play the third voice data corresponding to the target candidate reply text.

[0005] Preferably, determining the target task with the highest ranking in the unprocessed task queue includes: A target task with the highest ranking is determined in the unprocessed task queue, and the target task is moved to the processing task queue.

[0006] Preferably, the generating the first voice data based on the text reminder template corresponding to the target task includes: Determine the contract type of the target task, and obtain a text reminder template corresponding to the contract type; Extracting the contract parameter data of the target task based on the contract type, and filling the contract parameter data into the text reminder template to obtain text reminder data; The first voice data corresponding to the text reminder data is generated based on voice synthesis.

[0007] Preferably, the real-time display and updating of the displayed text data on the target interface includes: Extract key fields from the current text of the target text data to construct a current key field set; Querying a preset dictionary table based on the current key field set to obtain candidate reply texts matching the current key field set; The display text data is displayed in the target interface, and after the current key field set is updated, the display text data is updated in the target interface based on the updated current key field set.

[0008] Preferably, after displaying and updating the displayed text data in real time on the target interface, the method further includes: When the selection instruction is not received within the preset waiting time, a target candidate reply text is selected from each of the candidate reply texts based on the historical selection frequency, and the third voice data corresponding to the target candidate reply text is played.

[0009] Preferably, the method further comprises: Determining a minimum playback duration corresponding to the first voice data; When the call channel is interrupted within the minimum playback duration, obtaining a replay reminder template corresponding to the target task, randomly generating a verification code, and generating fourth voice data based on the verification code and the replay reminder template; A call request is initiated to the target terminal, the fourth voice data is played after the call channel is established, and the verification code is sent to the application account corresponding to the target terminal.

[0010] Preferably, the determining the minimum playback duration corresponding to the first voice data includes: The last keyword time node in the first voice data is determined based on the text reminder template, and the minimum playback duration is determined based on the keyword time node.

[0011] According to a second aspect, there is provided an intelligent reminder device based on speech synthesis, the device comprising: A receiving module, configured to, when receiving a processing instruction, respond to the processing instruction, determine the target task with the highest ranking in the unprocessed task queue, and generate first voice data based on a text reminder template corresponding to the target task; A first playing module, used to initiate a call request to a target terminal corresponding to the target task, and play the first voice data after a call channel is established; A display module, used to continuously acquire the second voice data of the target terminal, determine the target text data corresponding to the second voice data based on a preset natural language processing model, and display and update the display text data in real time on the target interface, wherein the display text data includes the target text data and candidate reply texts corresponding to the target text data, and the candidate reply texts are determined based on key fields of the target text data; The second playing module is used to receive and respond to the selection instruction for the candidate reply text, determine the target candidate reply text, and play the third voice data corresponding to the target candidate reply text.

[0012] According to a third aspect, there is provided an electronic device, comprising a processor and a memory; The processor is connected to the memory; The memory is used to store executable program code; The processor runs a program corresponding to the executable program code by reading the executable program code stored in the memory, so as to execute the steps of the method provided in the first aspect or any possible implementation manner of the first aspect.

[0013] According to a fourth aspect, a computer-readable storage medium is provided, on which a computer program is stored, and the computer-readable storage medium stores instructions, which, when the instructions are executed on a computer or a processor, cause the computer or the processor to execute the method provided in the first aspect or any possible implementation of the first aspect.

[0014] The method and device provided in the embodiments of this specification can intelligently generate corresponding voice data according to the text reminder template to initiate a call through speech synthesis, and convert the user's voice into text to display to the customer service staff. At the same time, different candidate reply texts will be displayed according to the real-time specific content of the text. The customer service staff only needs to select the preset candidate reply text according to the displayed text content to complete the reminder call for the user. Since the customer service staff only needs to control the call process according to the displayed text data, and does not need to be personally responsible for the call, the customer service staff can control the server to process multiple call tasks at the same time, which greatly improves the efficiency of telephone reminders and ensures that each telephone reminder task can be processed in a timely manner. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0016] Figure 1 It is a flowchart of an intelligent reminder method based on speech synthesis in one embodiment of this specification.

[0017] Figure 2 It is a structural diagram of an intelligent reminder device based on speech synthesis in one embodiment of this specification.

[0018] Figure 3 It is a structural diagram of an electronic device in one embodiment of this specification. DETAILED DESCRIPTION

[0019] The technical solutions 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.

[0020] In the following introduction, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance. The following introduction provides multiple embodiments of the present application, and different embodiments can be replaced or combined, so the present application can also be considered to include all possible combinations of the same and / or different embodiments recorded. Therefore, if one embodiment includes features A, B, and C, and another embodiment includes features B and D, then the present application should also be considered to include embodiments containing one or more of all other possible combinations of A, B, C, and D, although the embodiment may not be clearly recorded in the following text.

[0021] The following description provides examples and does not limit the scope, applicability or examples set forth in the claims. Changes may be made to the functions and arrangements of the elements described without departing from the scope of the present application. Various processes or components may be appropriately omitted, substituted or added to each example. For example, the described method may be performed in an order different from the order described, and various steps may be added, omitted or combined. In addition, features described in some examples may be combined in other examples.

[0022] See also Figure 1 , Figure 1 : is a flow chart of an intelligent reminder method based on speech synthesis provided in an embodiment of the present application. In an embodiment of the present application, the method includes: S101. When a processing instruction is received, respond to the processing instruction, determine the target task with the highest ranking in the unprocessed task queue, and generate first voice data based on a text reminder template corresponding to the target task.

[0023] The execution entity of this application can be a cloud server.

[0024] In the embodiment of the present specification, when the customer service staff needs the cloud server to perform intelligent call reminder, they can generate processing instructions by pressing keys on the terminal, and the terminal will send the processing instructions to the cloud server. After receiving the processing instructions, the cloud server will respond to the processing instructions to determine the target task with the highest current ranking in the unprocessed task queue of the server system. Each task in the unprocessed task queue is a call task for which the contract fulfillment date has arrived and a telephone reminder needs to be made to the corresponding user. Since there are many types of contracts, the types of tasks corresponding to different types of contracts will also be different. The cloud server will pre-store various text reminder templates set according to the types of each contract. The cloud server will obtain the corresponding text reminder template according to the task type of the target task, and convert the text reminder template into the first voice data through text-to-speech (TTS) technology, so that the intelligent call reminder process can be implemented through the first voice data later.

[0025] In one possible implementation, determining the target task with the highest ranking in the unprocessed task queue includes: A target task with the highest ranking is determined in the unprocessed task queue, and the target task is moved to the processing task queue.

[0026] In the embodiment of the present specification, after the cloud server determines the target task in the unprocessed task queue, it will start to execute the subsequent text-to-speech and dial-up call reminder process, that is, start to process the target task. Since multiple tasks can be processed simultaneously through the method of the present application scheme, in order to avoid the server repeatedly selecting the same task for processing in the unprocessed task queue, after the cloud server determines the target task in the unprocessed task queue and starts to process it, it will remove the target task from the unprocessed task queue and add it to the processing task queue.

[0027] In one possible implementation, the generating the first voice data based on the text reminder template corresponding to the target task includes: Determine the contract type of the target task, and obtain a text reminder template corresponding to the contract type; Extracting the contract parameter data of the target task based on the contract type, and filling the contract parameter data into the text reminder template to obtain text reminder data; The first voice data corresponding to the text reminder data is generated based on voice synthesis.

[0028] In the embodiments of this specification, tasks are divided into different contract types according to different contract types, and different contract types are pre-set with different text reminder templates to ensure that the content in the text reminder template can match the content that needs to be reminded for the contract of this type. After the cloud server determines the contract type of the target task, it can obtain the corresponding text reminder template according to the contract type. There may be several blank items in the text reminder template that need to be filled with parameter data, such as the time of expiration, the name of the user, etc. The cloud server needs to determine the type of parameters that need to be filled in the text reminder template according to the contract type, and then extract these contract parameter data from the task data corresponding to the target task, and fill the contract parameter data into the text reminder template to finally obtain the text reminder data. The text reminder data can be regarded as the text content corresponding to the voice that is finally played to the user. Then, the cloud server can convert the text reminder data into the first voice data by voice synthesis, so that the intelligent call reminder can be performed according to the first voice data in the future.

[0029] S102: Initiate a call request to a target terminal corresponding to the target task, and play the first voice data after a call channel is established.

[0030] In the embodiments of this specification, the target terminal is generally a mobile phone terminal. The cloud server determines the user corresponding to the target task and the target terminal used by the user according to the task data of the target task, and initiates a call request to the target terminal. After the call channel is established, that is, after the user answers the call, the cloud server plays the synthesized first voice data to realize the intelligent reminder process for the user, remind the user that the contract has expired and urge the user to fulfill the contract.

[0031] In other possible implementations, if the call channel cannot be established, that is, the user does not answer the call, the cloud server can also generate SMS data based on the text reminder template and / or text reminder data, and send the SMS data to the target terminal to remind the user via SMS.

[0032] S103: Continuously acquire the second voice data of the target terminal, determine the target text data corresponding to the second voice data based on a preset natural language processing model, and display and update the displayed text data in real time on the target interface.

[0033] The display text data includes the target text data and candidate reply texts corresponding to the target text data, and the candidate reply texts are determined based on key fields of the target text data.

[0034] In the embodiment of the present specification, after the user hears the first voice data played, he may be confused about the content of the first voice data. In the prior art, the cloud server can only mechanically play the content of the voice data, or the user needs to click the corresponding button on the target terminal to make a voice reply according to the corresponding preset reply text, and it is impossible to interact with the user in real time and effectively. Therefore, the purpose of the present application scheme is not to allow the cloud server to conduct mechanical and rigid calls completely autonomously, but to require customer service personnel to control the entire call process. Specifically, when the user speaks through the target terminal, the cloud server will continuously obtain the second voice data transmitted by the target terminal, and process and identify the second voice data through the natural language processing model to generate the target text data corresponding to the second voice data. Then, the cloud server can parse the user's current intention by extracting and identifying the key fields of the target text data, and then determine the candidate reply text corresponding to the extracted key fields through a pre-set database storing the mapping relationship between each key field and the candidate reply text, and display the target text data and the candidate reply text together on the target interface of the terminal used by the customer service personnel, so that the customer service personnel can judge the current conversation situation and make a decision on the reply content. There may be more than one candidate reply text corresponding to a key field.

[0035] Among them, the Natural Language Processing (NLP) model refers to a machine learning model used to process and understand human language. These models can process text, speech and other forms of natural language data, and perform various tasks such as language translation, sentiment analysis, text classification, intent recognition, etc. Specifically, the natural language processing model can use the Bag-of-Words model, Word Embedding model, Recurrent Neural Networks (RNN), Convolutional Neural Networks (CNN), Transformer model, Pre-trained Language Models, etc. Through a large amount of simulated conversation text and voice data trained natural language processing models, in addition to realizing voice-to-text translation conversion, it can also realize intent recognition by extracting keywords from text sentences. In other words, by inputting the second voice data into the trained natural language processing model, the target text data and the key fields corresponding to the target text data can be obtained. Then, by querying the key field in the database, the candidate reply text corresponding to the key field can be found.

[0036] It should be noted that the cloud server will continuously obtain the second voice data and continuously convert the second voice data into target text data. Therefore, it is possible that the semantic intent recognized by the natural language processing model changes after the first half of the sentence in the target text data is combined with the second half of the sentence converted in the next few seconds, which will cause the corresponding candidate reply text to change. Therefore, the cloud server will determine the target text data and the candidate reply text in real time, and display them in the target interface in real time. That is, when the content of the two changes, the cloud server will also update the content displayed on the target interface in real time.

[0037] In one possible implementation, the real-time display and updating of the displayed text data on the target interface includes: Extract key fields from the current text of the target text data to construct a current key field set; Querying a preset dictionary table based on the current key field set to obtain candidate reply texts matching the current key field set; The display text data is displayed in the target interface, and after the current key field set is updated, the display text data is updated in the target interface based on the updated current key field set.

[0038] In the embodiments of the present specification, due to the real-time update and change of the specific content in the target text data, the intention that the user wants to express may change. In order to ensure the accuracy and effectiveness of the candidate reply text, the cloud server should not determine the candidate reply text based on a certain key field, but should determine the candidate reply text in combination with all key fields. Therefore, the cloud server will construct the key fields in the current text obtained in real time into a current key field set, and query the preset dictionary table based on the current key field set to find the matching candidate reply text. The mapping relationship between each key field set and each candidate reply text can be pre-stored in the dictionary table.

[0039] Similarly, when the target text data is updated, resulting in an update to the current key field set, the cloud server will also re-determine the candidate reply texts and update the display text data displayed in the target interface.

[0040] S104, receiving and responding to a selection instruction for the candidate reply text, determining a target candidate reply text, and playing third voice data corresponding to the target candidate reply text.

[0041] In the embodiment of the present specification, the customer service staff can intuitively understand what the user said and the candidate reply text that can be selected according to the display text data displayed on the target interface. The customer service staff only needs to select the candidate reply text that is considered appropriate on the target interface through the operation on the terminal used by themselves, and a selection instruction will be generated and sent to the cloud server. After receiving the selection instruction, the cloud server will respond to the selection instruction, and determine the target candidate reply text selected by the customer service staff, convert it into the third voice data, and play the third voice data to the target terminal in the call channel. Through the above method, not only the work efficiency of the customer service staff is improved, but also the customer service staff only needs to select the candidate reply text on the target interface to control the content of multiple call processes at the same time, without having to make a phone call to remind in person, which improves the reminder efficiency and the timeliness of the reminder. Due to the operation of the customer service staff, the user's call answering experience and the actual call interaction effect are guaranteed, avoiding the problem that only fixed voice content can be played in the traditional way and it is difficult to interact with the user in real time, which leads to the poor effect of call reminder.

[0042] In one possible implementation, after displaying and updating the display text data in real time on the target interface, the method further includes: When the selection instruction is not received within the preset waiting time, a target candidate reply text is selected from each of the candidate reply texts based on the historical selection frequency, and the third voice data corresponding to the target candidate reply text is played.

[0043] In the embodiment of the present specification, after the cloud server displays the display text data in the target interface, if the customer service staff does not select the target candidate reply text within the specified waiting time, in order to ensure the user's real-time call experience, the cloud server will automatically select the target candidate reply text. Specifically, the cloud server will determine the frequency of each candidate reply text displayed at this time being selected in the historical database, and use the candidate reply text with the highest historical selection frequency as the target candidate reply text, and then generate the third voice data for playback with the target candidate reply text.

[0044] In one embodiment, the method further comprises: Determining a minimum playback duration corresponding to the first voice data; When the call channel is interrupted within the minimum playback duration, obtaining a replay reminder template corresponding to the target task, randomly generating a verification code, and generating fourth voice data based on the verification code and the replay reminder template; A call request is initiated to the target terminal, the fourth voice data is played after the call channel is established, and the verification code is sent to the application account corresponding to the target terminal.

[0045] In the embodiment of the present specification, the first voice data will correspond to a minimum playback time, which is not necessarily the time required to play the first voice data completely, but may also be the time required to play the key content in the first voice data. After the cloud server starts playing the first voice data, it will start timing. If the user hangs up the call channel of the terminal before the minimum playback time, the cloud server believes that the user may have doubts about the authenticity of the call content and directly hangs up the call. In this case, it can be considered that this call reminder has no reminder effect. Therefore, the cloud server will obtain the replay reminder template corresponding to the target task. Compared with the text reminder template, the replay reminder template can add text content such as "This call is a smart call made by the background of a certain APP, and the dynamic code is ABC. You can go to the APP to confirm the authenticity of this call after the call ends according to the dynamic code" at the beginning of the text, and generate the fourth voice data in combination with the randomly generated verification code, and initiate a call to the target terminal again. At the same time, the randomly generated verification code will also be sent to the application account of the target terminal in the corresponding application for the user to review.

[0046] In one possible implementation, determining the minimum playback duration corresponding to the first voice data includes: The last keyword time node in the first voice data is determined based on the text reminder template, and the minimum playback duration is determined based on the keyword time node.

[0047] In an embodiment of the present specification, the position of each keyword can be pre-marked in the text reminder template, and the cloud server can determine the time node corresponding to the last keyword in the first voice data through the mark, and the duration from the initial moment to the moment corresponding to the time node is the determined minimum playback duration.

[0048] The following will be combined with the attached Figure 2 , the intelligent reminder device based on speech synthesis provided in the embodiment of the present application is introduced in detail. It should be noted that the attached Figure 2 The intelligent reminder device based on speech synthesis shown is used to execute the present application Figure 1 For the convenience of explanation, only the part related to the embodiment of the present application is shown. For the specific technical details not disclosed, please refer to the present application. Figure 1 The embodiment shown.

[0049] See also Figure 2 , Figure 2 is a structural diagram of an intelligent reminder device based on speech synthesis provided in an embodiment of the present application. Figure 2 As shown, the device comprises: The receiving module 201 is used for, when receiving a processing instruction, responding to the processing instruction, determining the target task with the highest ranking in the unprocessed task queue, and generating first voice data based on the text reminder template corresponding to the target task; A first playing module 202, configured to initiate a call request to a target terminal corresponding to the target task, and play the first voice data after a call channel is established; A display module 203 is used to continuously acquire the second voice data of the target terminal, determine the target text data corresponding to the second voice data based on a preset natural language processing model, and display and update the display text data in real time on the target interface, wherein the display text data includes the target text data and candidate reply texts corresponding to the target text data, and the candidate reply texts are determined based on key fields of the target text data; The second playing module 204 is used to receive and respond to the selection instruction for the candidate reply text, determine the target candidate reply text, and play the third voice data corresponding to the target candidate reply text.

[0050] In one possible implementation, the receiving module 201 is specifically used for: A target task with the highest ranking is determined in the unprocessed task queue, and the target task is moved to the processing task queue.

[0051] In one possible implementation, the receiving module 201 is further configured to: Determine the contract type of the target task, and obtain a text reminder template corresponding to the contract type; Extracting the contract parameter data of the target task based on the contract type, and filling the contract parameter data into the text reminder template to obtain text reminder data; The first voice data corresponding to the text reminder data is generated based on voice synthesis.

[0052] In one possible implementation, the display module 203 is specifically used for: Extract key fields from the current text of the target text data to construct a current key field set; Querying a preset dictionary table based on the current key field set to obtain candidate reply texts matching the current key field set; The display text data is displayed in the target interface, and after the current key field set is updated, the display text data is updated in the target interface based on the updated current key field set.

[0053] In one possible implementation, the display module 203 is further used to: When the selection instruction is not received within the preset waiting time, a target candidate reply text is selected from each of the candidate reply texts based on the historical selection frequency, and the third voice data corresponding to the target candidate reply text is played.

[0054] In one embodiment, the device further comprises: A determination module, used to determine a minimum playback time corresponding to the first voice data; an acquisition module, configured to acquire, when the call channel is interrupted within the minimum playback duration, a replay reminder template corresponding to the target task, randomly generate a verification code, and generate fourth voice data based on the verification code and the replay reminder template; The third playing module is used to initiate a call request to the target terminal, play the fourth voice data after the call channel is established, and send the verification code to the application account corresponding to the target terminal.

[0055] In one possible implementation, the determination module is specifically used for: The last keyword time node in the first voice data is determined based on the text reminder template, and the minimum playback duration is determined based on the keyword time node.

[0056] Those skilled in the art can clearly understand that the technical solutions of the embodiments of the present application can be implemented with the help of software and / or hardware. The "unit" and "module" in this specification refer to software and / or hardware that can independently complete or cooperate with other components to complete specific functions, where the hardware can be, for example, a field programmable gate array (FPGA), an integrated circuit (IC), etc.

[0057] Each processing unit and / or module of the embodiments of the present application may be implemented by an analog circuit that implements the functions described in the embodiments of the present application, or may be implemented by software that executes the functions described in the embodiments of the present application.

[0058] See also Figure 3 , which shows a schematic diagram of the structure of an electronic device involved in an embodiment of the present application, the electronic device can be used to implement Figure 1 The method in the embodiment shown. Figure 3 As shown, the electronic device 300 may include: at least one processor 301 , at least one network interface 304 , a user interface 303 , a memory 305 , and at least one communication bus 302 .

[0059] The communication bus 302 is used to realize the connection and communication between these components.

[0060] The user interface 303 may include a display screen (Display) and a camera (Camera). Optionally, the user interface 303 may also include a standard wired interface and a wireless interface.

[0061] The network interface 304 may optionally include a standard wired interface or a wireless interface (such as a WI-FI interface).

[0062] Among them, the processor 301 may include one or more processing cores. The processor 301 uses various interfaces and lines to connect various parts of the entire electronic device 300, and executes various functions and processes data of the electronic device 300 by running or executing instructions, programs, code sets or instruction sets stored in the memory 305, and calling data stored in the memory 305. Optionally, the processor 301 can be implemented in at least one hardware form of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), and programmable logic array (Programmable Logic Array, PLA). The processor 301 can integrate one or a combination of a central processing unit (Central Processing Unit, CPU), a graphics central processing unit (Graphics Processing Unit, GPU) and a modem. Among them, the CPU mainly processes the operating system, user interface and application programs; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 301, and it can be implemented separately through a chip.

[0063] Among them, the memory 305 may include a random access memory (Random Access Memory, RAM) and may also include a read-only memory (Read-Only Memory). Optionally, the memory 305 includes a non-transitory computer-readable storage medium. The memory 305 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 305 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store data involved in the above-mentioned various method embodiments, etc. The memory 305 may also be optionally at least one storage device located away from the aforementioned processor 301. As Figure 3 As shown, the memory 305 as a computer storage medium may include an operating system, a network communication module, a user interface module, and program instructions.

[0064] exist Figure 3 In the electronic device 300 shown, the user interface 303 is mainly used to provide an input interface for the user and obtain the data input by the user; and the processor 301 can be used to call the intelligent reminder application based on speech synthesis stored in the memory 305, and specifically perform the following operations: When receiving a processing instruction, responding to the processing instruction, determining the target task with the highest ranking in the unprocessed task queue, and generating first voice data based on a text reminder template corresponding to the target task; Initiating a call request to a target terminal corresponding to the target task, and playing the first voice data after a call channel is established; Continuously acquiring second voice data of the target terminal, determining target text data corresponding to the second voice data based on a preset natural language processing model, and displaying and updating display text data in real time on a target interface, wherein the display text data includes the target text data and candidate reply texts corresponding to the target text data, wherein the candidate reply texts are determined based on key fields of the target text data; Receive and respond to a selection instruction for the candidate reply text, determine a target candidate reply text, and play the third voice data corresponding to the target candidate reply text.

[0065] The present application also provides 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 above method are implemented. The computer-readable storage medium may include, but is not limited to, any type of disk, including a floppy disk, an optical disk, a DVD, a CD-ROM, a micro drive, and a magneto-optical disk, a ROM, a RAM, an EPROM, an EEPROM, a DRAM, a VRAM, a flash memory device, a magnetic card or an optical card, a nanosystem (including a molecular memory IC), or any type of medium or device suitable for storing instructions and / or data.

[0066] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

[0067] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0068] In the several embodiments provided in the present application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of the units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some service interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0069] 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 on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0070] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0071] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a memory, including a number of instructions to enable a computer device (which can be a personal computer, server or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned memory includes: U disk, read-only memory (ROM), random access memory (RAM), mobile hard disk, disk or optical disk and other media that can store program codes.

[0072] A person skilled in the art may understand that all or part of the steps in the various methods of the above embodiments may be completed by entering a program to instruct related hardware, and the program may be stored in a computer-readable memory, which may include a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0073] The above is only an exemplary embodiment of the present disclosure, and the scope of the present disclosure cannot be limited thereto. That is, any equivalent changes and modifications made according to the teachings of the present disclosure are still within the scope of the present disclosure. After considering the specification and practicing the disclosure here, those skilled in the art will easily think of the implementation scheme of the present disclosure. This application is intended to cover any modification, use or adaptation of the present disclosure, which follows the general principles of the present disclosure and includes common knowledge or customary technical means in the technical field not recorded in the present disclosure. The description and examples are regarded as exemplary only, and the scope and spirit of the present disclosure are defined by the claims.

Claims

1. An intelligent reminder method based on speech synthesis, characterized in that: The method comprises: When receiving a processing instruction, responding to the processing instruction, determining the target task with the highest ranking in the unprocessed task queue, and generating first voice data based on a text reminder template corresponding to the target task; Initiating a call request to a target terminal corresponding to the target task, and playing the first voice data after a call channel is established; Continuously acquiring second voice data of the target terminal, determining target text data corresponding to the second voice data based on a preset natural language processing model, and displaying and updating display text data in real time on a target interface, wherein the display text data includes the target text data and candidate reply texts corresponding to the target text data, wherein the candidate reply texts are determined based on key fields of the target text data; Receive and respond to a selection instruction for the candidate reply text, determine a target candidate reply text, and play the third voice data corresponding to the target candidate reply text.

2. The method according to claim 1, characterized in that The step of determining the target task with the highest ranking in the unprocessed task queue includes: A target task with the highest ranking is determined in the unprocessed task queue, and the target task is moved to the processing task queue.

3. The method according to claim 1, characterized in that The generating the first voice data based on the text reminder template corresponding to the target task includes: Determine the contract type of the target task, and obtain a text reminder template corresponding to the contract type; Extracting the contract parameter data of the target task based on the contract type, and filling the contract parameter data into the text reminder template to obtain text reminder data; The first voice data corresponding to the text reminder data is generated based on voice synthesis.

4. The method according to claim 1, characterized in that The real-time display and updating of the displayed text data on the target interface includes: Extract key fields from the current text of the target text data to construct a current key field set; Based on the current key field set, a preset dictionary table is queried to obtain candidate reply texts matching the current key field set; The display text data is displayed in the target interface, and after the current key field set is updated, the display text data is updated in the target interface based on the updated current key field set.

5. The method according to claim 1, characterized in that After the target interface displays and updates the displayed text data in real time, the method further includes: When the selection instruction is not received within the preset waiting time, a target candidate reply text is selected from each of the candidate reply texts based on the historical selection frequency, and the third voice data corresponding to the target candidate reply text is played.

6. The method according to claim 1, characterized in that The method further comprises: Determining a minimum playback duration corresponding to the first voice data; When the call channel is interrupted within the minimum playback duration, obtaining a replay reminder template corresponding to the target task, randomly generating a verification code, and generating fourth voice data based on the verification code and the replay reminder template; A call request is initiated to the target terminal, the fourth voice data is played after the call channel is established, and the verification code is sent to the application account corresponding to the target terminal.

7. The method according to claim 6, characterized in that The determining a minimum playback duration corresponding to the first voice data includes: The last keyword time node in the first voice data is determined based on the text reminder template, and the minimum playback duration is determined based on the keyword time node.

8. An intelligent reminder device based on speech synthesis, characterized in that: The device comprises: A receiving module, configured to, when receiving a processing instruction, respond to the processing instruction, determine the target task with the highest ranking in the unprocessed task queue, and generate first voice data based on a text reminder template corresponding to the target task; A first playing module, used to initiate a call request to a target terminal corresponding to the target task, and play the first voice data after a call channel is established; A display module, used to continuously acquire the second voice data of the target terminal, determine the target text data corresponding to the second voice data based on a preset natural language processing model, and display and update the display text data in real time on the target interface, wherein the display text data includes the target text data and candidate reply texts corresponding to the target text data, and the candidate reply texts are determined based on key fields of the target text data; The second playing module is used to receive and respond to the selection instruction for the candidate reply text, determine the target candidate reply text, and play the third voice data corresponding to the target candidate reply text.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, wherein the computer-readable storage medium has instructions stored therein, and when the instructions are executed on a computer or a processor, the computer or the processor executes the steps of the method according to any one of claims 1 to 7.

Images