CN118433309B - Call information processing method, data response device and call information processing system - Google Patents

Abstract

The present application provides a call information processing method, a data response device, and a call information processing system, wherein the method comprises: determining a template to be spliced corresponding to the operation type according to the operation type input by the user, the template to be spliced comprising: at least one template string and a variable string, obtaining a template voice corresponding to the template string, and obtaining target data corresponding to the variable string from a real-time data storage device according to the identifier of the operation object input by the user, the template voice is pre-stored in the data response device, and the target data voice of the target data is determined according to the target data and the current voice database, the current voice database is dynamically updated by the voice update device and sent to the data response device, and the operation result of the operation object is generated and output according to the template voice and the target data voice. The present application can effectively reduce the configuration cost and resource pressure of the TTS server in the scenario of high concurrent requests.

Description

Call information processing method, data answering device and call information processing system

Technical Field

The present application relates to the field of computer technology, and in particular to a call information processing method, a data answering device, and a call information processing system.

Background Art

IVR (Interactive Voice Response) is a telephone technology that allows users to interact with computer systems through voice or key input. It has been applied in many real-time information scenarios, such as stock trading orders, product introductions, notification broadcasts, etc.

In the prior art, the content of the announcement is generally updated by requesting real-time TTS (Text To Speech). After the user initiates a query request to the IVR system, the IVR system queries the counter for real-time market information and requests TTS for the entire sentence from the corresponding TTS server.

However, in the prior art, if there are high-concurrency call requests, the TTS server and the IVR system need to be configured in equal proportion, which has a high cost problem. In addition, for high-concurrency call requests, requesting TTS for the entire sentence will also put great pressure on the TTS server resources.

Summary of the invention

The purpose of this application is to provide a call information processing method, a data answering device and a call information processing system to address the deficiencies in the above-mentioned prior art, so as to solve the problems in the prior art of high TTS server deployment cost and high resource pressure in IVR broadcast scenarios with high concurrency.

To achieve the above purpose, the technical solution adopted in this application is as follows:

In a first aspect, the present application provides a call information processing method, which is applied to a data answering device, and the method includes:

Determine, according to the operation type input by the user, a template to be spliced corresponding to the operation type, wherein the template to be spliced includes: at least one template string and a variable string;

Acquire the template voice corresponding to the template character string, and acquire the target data corresponding to the variable character string from the real-time data storage device according to the identifier of the operation object input by the user, wherein the template voice is pre-stored in the data response device;

Determine the target data voice of the target data according to the target data and the current voice database, the current voice database is dynamically updated by the voice updating device and sent to the data response device;

An operation result of the operation object is generated and output according to the template voice and the target data voice.

Optionally, the process of the voice updating device dynamically updating the current voice database includes:

Acquire a current data file based on a preset period, and determine whether the current voice database needs to be updated according to the current data file;

If so, the current voice database is updated according to the current data file to obtain an updated current voice database, and the updated current voice database is sent to each of the data response devices.

Optionally, determining whether the current voice database needs to be updated according to the current data file includes:

Comparing the current data file with the data file of the current voice database to determine whether the current data file is the same as the data file of the current voice database;

If they are the same, the current voice database needs to be updated; if they are not the same, the current voice database does not need to be updated.

Optionally, the updating the current voice database according to the current data file to obtain an updated current voice database includes:

Determine at least one update data according to the current data file and the data file of the current voice database;

Sending the at least one updated data to a voice conversion device to obtain voice information of each updated data;

The current voice database is updated according to the voice information of each update data to obtain the updated current voice database.

Optionally, sending the updated current voice database to each of the data response devices comprises:

Determining at least one data response device to be updated according to a pre-stored data response device list and an activation state of each of the data response devices;

The updated current voice database is sent to each of the data response devices to be updated.

Optionally, the acquiring the template voice corresponding to the template character string includes:

The template speech corresponding to the template character string is searched from a template speech library, wherein the template speech library includes: a plurality of template character strings and speech information corresponding to each template character string.

Optionally, the step of acquiring target data corresponding to the variable character string from a real-time data storage device according to an identifier of an operation object input by a user includes:

Searching the real-time data storage device for the selected data corresponding to the identifier of the operation object;

Arrange the selected data in the order of the variable character strings to obtain the target data.

Optionally, determining the target data voice of the target data according to the target data and the current voice database includes:

The target data voice corresponding to the target data is searched in the current voice database.

Optionally, the target data is the value of the variable string;

The step of generating and outputting an operation result of an operation object according to the template voice and the target data voice includes:

The template voice is filled into the position corresponding to the template character string, and the target data voice is filled into the position corresponding to the variable character string to obtain the operation result of the operation object.

In a second aspect, the present application provides a data response device, the device comprising:

A first determination module is used to determine, according to an operation type input by a user, a template to be spliced corresponding to the operation type, wherein the template to be spliced includes: at least one template string and a variable string;

An acquisition module, used to acquire the template voice corresponding to the template character string, and acquire the target data corresponding to the variable character string from the real-time data storage device according to the identifier of the operation object input by the user, wherein the template voice is pre-stored in the data response device;

A second determination module, for determining the target data voice of the target data according to the target data and a current voice database, wherein the current voice database is dynamically updated by a voice updating device and sent to the data response device;

A generating module is used to generate and output the operation result of the operation object according to the template voice and the target data voice.

Optionally, the acquisition module is specifically used for:

The template speech corresponding to the template character string is searched from a template speech library, wherein the template speech library includes: a plurality of template character strings and speech information corresponding to each template character string.

Optionally, the acquisition module is specifically used for:

Searching the real-time data storage device for the selected data corresponding to the identifier of the operation object;

Arrange the selected data in the order of the variable character strings to obtain the target data.

Optionally, the second determining module is specifically configured to:

The target data voice corresponding to the target data is searched in the current voice database.

Optionally, the target data is the value of the variable string;

The generation module is specifically used for:

The template voice is filled into the position corresponding to the template character string, and the target data voice is filled into the position corresponding to the variable character string to obtain the operation result of the operation object.

In a third aspect, an embodiment of the present application further provides a call information processing system, including a data response device, a real-time data storage device, a voice updating device, and a voice conversion device as in the method of the first aspect.

In a fourth aspect, an embodiment of the present application further provides an electronic device, comprising: a processor, a storage medium and a bus, wherein the storage medium stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor communicates with the storage medium through the bus, and the processor executes the machine-readable instructions to perform the steps of the call information processing method as described in any one of the first aspects.

In a fifth aspect, an embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the call information processing method as described in any one of the first aspects are executed.

The beneficial effects of the present application are: by storing the template voice of the fixed template string in the template to be spliced in the data response device, and after obtaining the target data from the real-time data storage device, the target data is converted to voice based on the pre-stored current voice database, the processing process of voice conversion can be completed locally in the data response device, so that the data response device does not need to make a whole sentence request to the TTS server, and there is no network delay for the data response device to make a whole sentence request to TTS, thereby reducing the delay. And the voice conversion process in the present application is completed locally by the data response device, even in the scenario of high concurrent request, it is not necessary to configure too many TTS resources, so that a single-channel TTS resource can meet high concurrent requests, and the cost of TTS server deployment is reduced. In the present application, the data response device pre-stores the voice file, so it only needs to obtain real-time data from the real-time data storage device, complete the voice conversion of the template string and the target data, and splice the voice to complete the whole sentence voice conversion, which effectively improves the real-time and reliability of voice broadcasting. In addition, the present application pre-processes the voice of the data through the voice updating device, so that the data response device is decoupled from the TTS server, simplifying the entire voice broadcast process.

In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, preferred embodiments are specifically cited below and described in detail with reference to the attached drawings.

BRIEF DESCRIPTION OF THE DRAWINGS

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

FIG1 is a schematic diagram showing an IVR broadcast in the prior art provided by an embodiment of the present application;

FIG2 shows a schematic diagram of the architecture of a call information processing system provided in an embodiment of the present application;

FIG3 shows a flow chart of a call information processing method provided in an embodiment of the present application;

FIG4 shows a flow chart of updating a current voice database provided by an embodiment of the present application;

FIG5 shows a flow chart of determining whether the current voice database needs to be updated according to an embodiment of the present application;

FIG6 shows a flow chart of updating a current voice database provided by an embodiment of the present application;

FIG7 shows a flow chart of synchronizing a current voice database provided by an embodiment of the present application;

FIG8 shows a flow chart of obtaining target data provided by an embodiment of the present application;

FIG9 shows a schematic structural diagram of a data response device provided in an embodiment of the present application;

FIG10 shows a schematic diagram of the structure of a voice updating device provided in an embodiment of the present application;

FIG. 11 shows a schematic structural diagram of an electronic device provided in an embodiment of the present application.

DETAILED DESCRIPTION

To make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. The components of the embodiments of the present application generally described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application claimed for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present application.

It should be noted that the term "comprising" will be used in the embodiments of the present application to indicate the existence of the features declared thereafter, but does not exclude the addition of other features.

At present, when the IVR system processes the user's call service, it generally sends the text information directly to the TTS for broadcasting. As shown in FIG1 , it is a process of implementing real-time update of IVR broadcast content in the prior art.

Taking the stock query scenario as an example, referring to Figure 1, after the user initiates a query request to the IVR system by phone, the IVR system can query the real-time market data of the stock code from the trading counter based on the stock code entered by the user, and send the market data text of the stock code to the TTS server for a whole sentence voice request, for example, sending "123456XX electronics, current price 123.4, buy price 132.9, sell price 123.4" to the TTS server, so that the TTS server can perform voice conversion on the whole sentence of the market data text, and send the converted voice to the IVR system, and the IVR system will broadcast the converted voice to the user.

However, during this process, when there are multiple IVR systems making concurrent requests to the TTS server, the TTS server needs to have the ability to handle high-concurrency requests. Due to the performance limitations of the TTS server, in order to improve the response speed of the TTS service in high-concurrency request scenarios and ensure timely updates of telephone broadcast content information, it is necessary to configure the IVR system and TTS server proportionally, which will undoubtedly greatly increase the server cost.

Furthermore, since the IVR system in the prior art always makes whole-sentence requests to the TTS server, the TTS server needs to process a large number of voice conversion tasks simultaneously in a high-concurrency scenario, which will also reduce the processing efficiency of telephone query requests, thereby affecting the user experience.

Based on this, the present application proposes a call information processing method, which is applied to a call information processing system. FIG2 is a schematic diagram of the architecture of a call information processing system provided by the present application. As shown in FIG2, the call information processing system includes: a data answering device, a real-time data storage device, a voice updating device, and a voice conversion device.

Taking the stock telephone inquiry scenario as an example, the data answering device can be an IVR system, the real-time data storage device can be a trading counter, the voice conversion device can be a TTS server, and the voice updating device can be used to store pre-recorded voice of data and update the pre-recorded voice.

In the present application, after the user initiates a telephone query request to the data response device, the data response device can query the market data corresponding to the stock code from the real-time data storage device based on the stock code entered by the user. At the same time, the data response device can also determine the recording template based on the query request initiated by the user, and determine the fixed amount of voice information in the recording template.

The data response device can store the voice package last updated by the voice update device, and determine the voice information of the market data based on the voice package, and then splice the voice information of the market data and the fixed amount of voice information in the recording template to obtain the voice result of the stock code queried by the user.

The voice updating device can update the voice information for the changed data based on the market information of the day, and push the updated voice package to each data response device when the voice information update reaches a certain amount.

The present application splits the entire sentence query request into fixed quantities and variables, and performs voice conversion on the fixed quantities and variables based on voice packets respectively. The IVR system can directly perform voice conversion when receiving the user's query request. In this way, when processing high-concurrency requests, the IVR system does not have to send the entire sentence request to the TTS server for voice conversion, thereby reducing the processing pressure of the TTS server and improving the efficiency of processing user call requests.

Next, in conjunction with FIG. 3 , the call information processing method of the present application is described. The method can be applied to the data answering device shown in FIG. 2 . As shown in FIG. 3 , the method includes:

S301. Determine a template to be spliced corresponding to the operation type according to the operation type input by the user, where the template to be spliced includes: at least one template string and a variable string.

The user can input the operation type through voice input, key input, etc. Each operation type corresponds to a different answer text template. Taking the scenario of stock phone inquiry as an example, the operation types input by the user may include: stock inquiry operation, transaction operation, account information inquiry operation, etc.

The template to be spliced may be an answer text template corresponding to the operation type, including at least one template string and a variable string. The template string may be a fixed value in the answer text template, and the variable string may be a variable value in the answer text template. The value of the variable string may be determined based on current real-time data.

For example, assuming that the operation type input by the user is "stock query operation", the template to be spliced corresponding to the operation type is "%stock_code %stock_name current price %current_price yuan, buy price %buy_price yuan, sell price %sell_price yuan", where the template string includes: "current price, yuan, buy price, sell price", and the variable string includes: "stock_code, stock_name, current_price, buy_price, sell_price".

S302, obtaining a template voice corresponding to the template character string, and obtaining target data corresponding to the variable character string from a real-time data storage device according to an identifier of an operation object input by a user, wherein the template voice is pre-stored in a data response device.

Optionally, the template voice corresponding to the template character string can be pre-stored in the data response device. Continuing with the above example, the voice encoding can be uniformly started with 1020, 1020001.pcma recording file content is the template voice of "current price", 1020002.pcma recording content is the template voice of "buy first price", 1020003.pcma recording content is the template voice of "sell first price", 1020004.pcma recording content is the template voice of "yuan". The recording file of the template voice can adopt the pcma encoding format, which is a common lossless encoding format of call centers. No special encoding and decoding processing is required for recording or splicing, thereby improving the processing efficiency of voice conversion.

The real-time data storage device can be a device for storing real-time data in Figure 2, such as a database for storing real-time data, or an electronic device for storing real-time data. In the stock telephone inquiry scenario, the real-time data storage device can be a trading counter, which is used to store stock codes and current market data of the stocks represented by each stock code, including the name of the stock code, current price, buy price, sell price, etc.

The identifier of the operation object input by the user may be a unique code or name of the operation object, etc., and the target data may be the current value of the variable string in the real-time data storage device.

Continuing with the example of the stock phone inquiry scenario, the identifier of the operation object may be a stock code. After the user enters the stock code, the data response device may send the stock code to the real-time data storage device to obtain the current market data of the stock represented by the stock code.

As a possible implementation method, the format of the target data returned by the real-time data storage device can be the same as the format of the template to be spliced in the data response device, that is, the target data corresponds one-to-one to the variable string in the template to be spliced, and the target data is arranged in the same order as the variable string in the template to be spliced.

As another possible implementation, the real-time data storage device may store data and variable strings corresponding to the data. The data response device may send both the identification of the operation object and the variable string to the real-time data storage device, and the real-time data storage device may determine all current data of the operation object based on the identification of the operation object, and determine the target data that needs to be returned to the data response device from all the current data based on the variable string.

S303, determining the target data voice of the target data according to the target data and the current voice database, the current voice database is dynamically updated by the voice updating device and sent to the data response device.

The current voice database can store numbers and voice files corresponding to the numbers, names of operation objects and voice files corresponding to the names, other text information of the operation objects and voice files corresponding to the text information. Continuing with the example of a stock phone query, the name of the operation object can be the name of the stock of the operation object, and the other text information of the operation object can be market news, company information, etc. of the stock.

The target data voice may include at least one voice file, each voice file is arranged in the order of the character string in the target data, and the pronunciation content of each voice file is the pronunciation of the character string in the target data.

After determining the target data, the target data can be converted into voice based on the current voice database, the numbers in the target data can be converted into voice according to the numbers stored in the current voice database and the voice files corresponding to the numbers, and the text in the target data can be converted into voice according to the text stored in the current voice database and the voice files corresponding to the text.

The voice updating device can update the current voice database when the data in the current voice database changes, and synchronously push the updated current voice database to the data response device.

S304: Generate and output the operation result of the operation object according to the template voice and the target data voice.

The data response device performs voice conversion on the template string to obtain the template voice, and performs voice conversion on the target data corresponding to the variable string to obtain the target data voice. After that, the template voice and the target data voice can be spliced according to the format of the template to be spliced to obtain the operation result of the operation object.

The operation result of the operation object may be a voice file of the operation result. For example, when a user performs a stock query, the voice broadcast content of the query result of the operation object may be returned.

In an embodiment of the present application, according to the operation type input by the user, a template to be spliced corresponding to the operation type is determined, and the template to be spliced includes: at least one template string and a variable string, a template voice corresponding to the template string is obtained, and according to the identifier of the operation object input by the user, the target data corresponding to the variable string is obtained from the real-time data storage device, the template voice is pre-stored in the data response device, and the target data voice of the target data is determined according to the target data and the current voice database. The current voice database is dynamically updated by the voice updating device and sent to the data response device, and the operation result of the operation object is generated and output according to the template voice and the target data voice.

By storing the template voice of the fixed template string in the template to be spliced in the data response device, and after obtaining the target data from the real-time data storage device, the target data is converted to voice based on the pre-stored current voice database, the voice conversion process can be completed locally on the data response device, so that the data response device does not need to make a whole sentence request to the TTS server, and there is no network delay for the data response device to make a whole sentence request to TTS, thereby reducing the delay. In addition, the voice conversion process in the present application is completed locally by the data response device, even in the scenario of high concurrent requests, there is no need to configure too many TTS resources, so that a single-channel TTS resource meets high concurrent requests, and reduces the cost of TTS server deployment. In the present application, the data response device pre-stores the voice file, so it only needs to obtain real-time data from the real-time data storage device, complete the voice conversion of the template string and the target data, and splice the voice to complete the whole sentence voice conversion, which effectively improves the real-time and reliability of the voice broadcast. In addition, the present application pre-processes the voice of the data through the voice update device, so that the data response device is decoupled from the TTS server, simplifying the entire voice broadcast process.

Next, the process of the above-mentioned voice updating device dynamically updating the current voice database is described. As shown in FIG4 , the process includes:

S401: Acquire a current data file based on a preset period, and determine whether a current voice database needs to be updated according to the current data file.

The current data file includes the identifiers of all operation objects, the names of the operation objects, and the text information of the operation objects. The voice updating device can store the current data file obtained last time, and compare the current data file obtained last time with the current data file obtained this time to determine whether the current voice database needs to be updated.

As a possible implementation manner, if the amount of data difference between the current data file obtained last time and the current data file obtained this time is greater than a first preset value, it can be determined that the current voice database needs to be updated.

The current voice database may be a voice package of the current data file acquired last time, including data in the current data file and a voice file corresponding to the data.

S402: If yes, then update the current voice database according to the current data file to obtain an updated current voice database, and send the updated current voice database to each data response device.

The updating process of the current voice database according to the current data file may be to determine the changed data in the current data file, and to update the current voice database based on the changed data.

In the first implementation, only the changed data may be incrementally updated, specifically by performing voice conversion on the changed data to obtain a voice file, and updating the current voice database based on the voice file of the changed data to obtain an updated current voice database.

In the second implementation method, when the amount of changed data is greater than the second preset value, it means that a large amount of data has changed between the current data file obtained this time and the current data file obtained last time. At this time, the current voice database can be fully updated, specifically, all the data in the current data file obtained this time is converted into voice to obtain an updated current voice database.

In the embodiment of the present application, the voice updating device updates the current voice database based on the current data file obtained this time and the current data file obtained last time, which can save the resources of the voice conversion device. Since the data that changes every day is generally small, the data that needs to be updated can be queued. Therefore, only the resources of one voice conversion device are needed to quickly complete the update of the entire current voice database, thereby improving the efficiency of voice conversion.

The following is a further description of the above-mentioned determination of whether the current voice database needs to be updated according to the current data file. As shown in FIG. 5 , the above-mentioned step S401 includes:

S501: Compare a current data file with a data file of a current voice database to determine whether the current data file is identical to the data file of the current voice database.

S502: If they are the same, the current voice database needs to be updated; if they are not the same, the current voice database does not need to be updated.

The data file of the current voice database may be the current data file acquired last time by the current voice database.

In the first implementation, the file hash value of the current data file and the file hash value of the data file of the current voice database can be calculated, and the hash values can be compared to see if they are the same. If they are the same, it means that the file contents are the same; if they are different, it means that there are differences in the file contents.

In the second implementation, the current data file and the data file of the current voice database can be compared byte by byte. For example, the characters of "XX Electronics" in the current data file are matched one by one in the data file of the current voice database. If "XX Electronics" does not exist in the data file of the current voice database, "XX Electronics" is used as an updated data. If "XX Electronics" exists in the data file of the current voice database, the next character string is compared until all character strings in the current data file are compared.

After determining that the current voice database needs to be updated, the current voice database can be updated according to the current data file to obtain an updated current voice database. As shown in FIG6 , the above step S402 includes:

S601. Determine at least one update data according to a current data file and a data file of a current voice database.

It is worth noting that, in the second implementation of step S502, while performing data comparison to determine that the current voice database needs to be updated, the changed data can be obtained synchronously. As a possible implementation, when the number of updated data is greater than a first preset value, it can be determined that the current voice database needs to be updated, and the changed data determined during the data comparison is used as the updated data.

The updated data may be new data in the current data file compared to the data file of the current voice database, data with modified data content, and the like.

It should be noted that the data identifier can be used to uniquely distinguish the data, so when determining whether the data content has been modified, the data with the same identifier in the current data file and the data file of the current voice database can be compared to determine whether the data content has been modified. It is also possible to compare based on the data identifier to determine the new data in the current data file compared to the data file of the current voice database, that is, the identifier included in the current data file and not included in the data file of the current voice database.

S602: Send at least one updated data to a voice conversion device to obtain voice information of each updated data.

The voice information of the updated data may be a voice file of the updated data.

2 , the voice updating device may send the update data to the voice conversion device, which performs voice conversion on the update data to obtain voice files of each update data.

For example, assuming that "XX Electronics" in the data file of the current voice database is changed to "XX Technology", "XX Technology" can be used to make a request to the voice conversion device, and the voice conversion device will perform voice conversion on "XX Technology" to obtain the voice file of "XX Technology" and return the voice file to the voice update device.

S603: Update the current voice database according to the voice information of each update data to obtain an updated current voice database.

For newly added data, the newly added data and the voice information of the newly added data can be added to the current voice database. For data with modified content, the data and the voice information of the data in the current voice database can be replaced, thereby completing the update process of the current voice database.

After completing the update process of the current voice database, the voice update device may send the updated current voice database to each data response device, as shown in FIG7 . The process includes:

S701: Determine at least one data response device to be updated according to a pre-stored data response device list and the activation status of each data response device.

The voice updating device may pre-configure multiple data response device lists, which include multiple data response devices that have established communication with the voice updating device and the device addresses of each data response device, wherein the device address of the data response device may be the ssh address or FTP directory of the IVR system.

For example, if there are 10 IVR systems, the data response device list includes 10 rows of data. The user can also modify the list, such as adding a new data response device or deleting a data response device.

When the data response device is just connected to the voice updating device, the voice updating device can initialize and update the data response device, and send the current voice database in full to the data response device.

As a possible implementation manner, the voice updating device may obtain the activation status of each data response device based on the device address of each data response device, and use the data response device whose activation status is activated as the data response device to be updated.

S702: Send the updated current voice database to each data response device to be updated.

In a first implementation, the voice updating device may update the current voice database based on the updated data and the voice information of the data, and send the updated current voice database to each data response device to be updated.

For example, assuming that the updated data "XX Technology" is identified as "600570", and the voice file of the updated data is "600570.pcma file", the voice updating device can replace the voice file identified as "600570" in the current voice database with "600570.pcma file" to obtain the updated current voice database.

In the second implementation, the voice updating device may also directly send the updated data and the voice information of the data to each data response device to be updated, and each data response device updates the current voice database based on the updated data and the voice information of the data.

For example, assuming that the updated data "XX Technology" is identified as "600570", and the voice file of the updated data is "600570.pcma file", the voice updating device can send the voice file identified as "600570" to each data response device to be updated, and each data response device will replace the voice file identified as "600570" with "600570.pcma file" to obtain the updated current voice database.

It is worth noting that in order to improve the stability and reliability of the call information processing system, the voice update device can also add an exception handling mechanism when requesting the voice conversion device to perform voice synthesis and push data to the data answering device. Specifically, the error information can be recorded in the log, and the current voice conversion task or data synchronization task can be postponed after three failed retries. After a round of update tasks is completed, the error information is sent through the interface to alert the relevant personnel, and the unsuccessful synthesis/synchronization tasks are cyclically retried.

Next, the processing process in the above data response device is described. The process of obtaining the template voice corresponding to the template character string in the above step S302 includes:

A template voice corresponding to a template character string is searched from a template voice library, wherein the template voice library includes: a plurality of template characters and voice information corresponding to each template character string.

The template voice library includes template strings and voice files corresponding to the template strings.

It is worth noting that the template character string and the voice file of the template character string can also be stored in the current voice database of the data response device. The template voice database and the current voice database can be the same database or different databases.

As a possible implementation method, the template string can have an identifier for uniquely distinguishing the string. The template voice library can store the identifier of the template string and the voice file of the template string. The identifier corresponds to the voice file one by one. When querying the template voice corresponding to the template string, the identifier of the template string can be found from the template voice library, and the voice file corresponding to the identifier is used as the template voice of the template string. Among them, the identifier can be the hash value of the template string or the template string itself, which is not limited in this application.

The following is a further explanation of the above-mentioned acquisition of target data corresponding to the variable string from the real-time data storage device according to the identifier of the operation object input by the user. In the first implementation, the data to be selected may be all data corresponding to the identifier of the operation object in the real-time data storage device. The data stored in the real-time data storage device and the order of the data may be the same as the data corresponding to the variable string in the template to be spliced. In this case, the data may be directly acquired based on the identifier of the operation object, and the data corresponding to the identifier may be determined as the data to be selected.

In the second implementation, the data stored in the real-time data storage device is more than the data corresponding to the variable string in the template to be spliced. At this time, as shown in FIG. 8 , the above step S302 includes:

S801. Search for the candidate data corresponding to the identifier of the operation object from the real-time data storage device.

S802: Arrange the candidate data in the order of the variable character string to obtain the target data.

The real-time data storage device includes: the identification of the operation object and the real-time data of the operation object. For example, the identification of the operation object, that is, the stock code is "123456", and the data corresponding to "123456" in the real-time data storage device is "123456|XX Electronics|123.4|132.9|123.4".

When the data stored in the real-time data storage device is more than the data corresponding to the variable string in the template to be spliced, the data response device can also send the variable string to be requested to the real-time data storage device, so that the real-time data storage device can obtain data from the corresponding field based on the variable string. The field of the data in the real-time data storage device can be the same as the variable name of the variable string.

For example, assuming that the user needs to query the current price of the stock code "123456", the data response device can send the stock code "123456", the variable string "current_price" of the current price, and the variable string "buy_price" of the buy price to the real-time data storage device. After the real-time data storage device determines the data based on "123456", it can continue to match the data fields based on the variable strings "current_price" and "buy_price" to obtain the selected data.

In another implementation, the real-time data storage device can also return all data to the data response device in the form of key-value pairs. The key of the key-value pair can be the field of the data, and the value of the key-value pair can be the value of the data. The data response device matches the data based on the variable string and determines that the data that is the same as the variable string field is the selected data.

After determining the data to be selected, the data to be selected can be arranged according to the arrangement order of the variable character strings in the template to be spliced to obtain the target data.

The step of determining the target data voice of the target data according to the target data and the current voice database includes:

Search the target data voice corresponding to the target data from the current voice database.

The current voice database stores data and voice files of the data.

It is worth noting that the current voice database can store single numbers and voice files of single numbers. For example, the voice files of the numbers "1, 2, 3, 4, 5, 6, 7, 8, 9, 0" are "901.pcma, 902.pcma, 903.pcma, 904.pcma, 905.pcma, 906.pcma, 907.pcma, 908.pcma, 909.pcma, 900.pcma" respectively, and the target data voice of the target data 123.4 is "901.pcma, 902.pcma, 903.pcma, 910.pcma, 904.pcma", among which the pronunciation content of 910.pcma is "dot".

When storing text and the voice files corresponding to the text, phrases and the voice information corresponding to the phrases may be stored. For example, the target data voice of the target data "XX Electronics" is the voice file "11023.pcma", and the pronunciation content is "XX Electronics".

Optionally, the target data is the value of the variable string.

After the data response device obtains the target data, it can assign the target data to the variable string. For example, the text returned by the real-time data storage device is "123456|XX Electronics|123.4|132.9|123.4". The data response device can use the text string to assign values to the variables according to the agreed format: Stock_code = 123456, stock_name = XX Electronics, current_price = 123.4, buy_price = 132.9, sell_price = 123.4.

The above process of generating and outputting the operation result of the operation object according to the template voice and the target data voice includes:

Fill the template voice into the position corresponding to the template string, fill the target data voice into the position corresponding to the variable string, and obtain the operation result of the operation object.

In the present application, the data response device can splice the voice files of each template string and the voice files of the variable string in order according to the order of the template string and the variable string in the template to be spliced, so as to obtain the operation result of the operation object.

Based on the same inventive concept, a call information processing device corresponding to the call information processing method is also provided in the embodiment of the present application. Since the principle of solving the problem by the device in the embodiment of the present application is similar to the above-mentioned call information processing method in the embodiment of the present application, the implementation of the device can refer to the implementation of the method, and the repeated parts will not be repeated.

FIG. 9 shows a schematic diagram of the structure of a call information processing device provided in an embodiment of the present application.

The first determination module 901 is used to determine, according to the operation type input by the user, a template to be spliced corresponding to the operation type, where the template to be spliced includes: at least one template string and a variable string;

The acquisition module 902 is used to acquire the template voice corresponding to the template character string, and acquire the target data corresponding to the variable character string from the real-time data storage device according to the identifier of the operation object input by the user, and the template voice is pre-stored in the data response device;

The second determination module 903 is used to determine the target data voice of the target data according to the target data and the current voice database, the current voice database is dynamically updated by the voice updating device and sent to the data response device;

The generating module 903 is used to generate and output the operation result of the operation object according to the template voice and the target data voice.

Optionally, the acquisition module 902 is specifically used for:

A template voice corresponding to a template character string is searched from a template voice library, wherein the template voice library includes: a plurality of template characters and voice information corresponding to each template character string.

Optionally, the acquisition module 902 is specifically used for:

Searching for the selected data corresponding to the identifier of the operation object from the real-time data storage device;

Arrange the candidate data in the order of the variable character string to obtain the target data.

Optionally, the second determining module 903 is specifically configured to:

Search the target data voice corresponding to the target data from the current voice database.

Optionally, the target data is the value of the variable string;

The generation module 903 is specifically used for:

Fill the template voice into the position corresponding to the template string, fill the target data voice into the position corresponding to the variable string, and obtain the operation result of the operation object.

The embodiment of the present application further provides a structural diagram of a voice updating device, as shown in FIG10 , the voice updating device includes a third determining module 1001 and an updating module 1002, wherein:

The third determination module 1001 is used to obtain the current data file based on a preset period, and determine whether the current voice database needs to be updated according to the current data file;

The updating module 1002 is used for updating the current voice database according to the current data file to obtain an updated current voice database, and sending the updated current voice database to each data response device.

Optionally, the third determining module 1001 is specifically configured to:

Comparing the current data file with the data file of the current voice database to determine whether the current data file is the same as the data file of the current voice database;

If they are the same, the current voice database needs to be updated; if they are not the same, the current voice database does not need to be updated.

Optionally, the updating module 1002 is specifically configured to:

Determine at least one update data according to the current data file and the data file of the current voice database;

Sending at least one updated data to the voice conversion device to obtain voice information of each updated data;

The current voice database is updated according to the voice information of each update data to obtain an updated current voice database.

Optionally, the updating module 1002 is specifically configured to:

Determining at least one data response device to be updated according to a pre-stored data response device list and an activation state of each data response device;

The updated current voice database is sent to each data response device to be updated.

In the embodiment of the present application, the template voice of the fixed template string in the template to be spliced is stored in the data response device, and after obtaining the target data from the real-time data storage device, the target data is converted to voice based on the pre-stored current voice database, so that the processing process of voice conversion can be completed locally in the data response device, so that the data response device does not need to make a whole sentence request to the TTS server, and there is no network delay for the data response device to make a whole sentence request to TTS, thereby reducing the delay. In addition, the voice conversion process in the present application is completed locally by the data response device, even in the scenario of high concurrent requests, there is no need to configure too many TTS resources, so that a single-channel TTS resource meets high concurrent requests, and the cost of TTS server deployment is reduced. In the present application, the data response device pre-stores the voice file, so it only needs to obtain real-time data from the real-time data storage device, complete the voice conversion of the template string and the target data, and splice the voice to complete the whole sentence voice conversion, which effectively improves the real-time and reliability of voice broadcasting. In addition, the present application pre-processes the voice of the data through the voice update device, so that the data response device is decoupled from the TTS server, simplifying the entire voice broadcasting process.

An embodiment of the present application also provides a call information processing system. Referring to FIG. 2 , the call information processing system includes a real-time data storage device, a voice updating device, a voice conversion device, and at least one data response device. The data response device may be the IVR system in FIG. 2 .

Figure 11 shows a schematic diagram of the structure of an electronic device provided in an embodiment of the present application, including: a processor 1101, a storage medium 1102 and a bus 1103, wherein the storage medium 1102 stores machine-readable instructions executable by the processor 1101. When the electronic device runs the call information processing method in the embodiment, the processor 1101 communicates with the storage medium 1102 through the bus 1103, and the processor 1101 executes the machine-readable instructions and the preamble of the method item of the processor 1101 to execute the steps of the above-mentioned call information processing method.

The embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored. The computer program is executed when a processor is running, and the processor executes the steps of the above-mentioned call information processing method.

In the embodiment of the present application, the computer program can also execute other machine-readable instructions when run by the processor to execute other methods described in the embodiment. For the specific execution method steps and principles, please refer to the description of the embodiment, which will not be repeated here.

In the embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, 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 communication interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

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.

In addition, each functional unit in the embodiments provided in 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.

If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage media include: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, and other media that can store program codes.

It should be noted that similar numbers and letters represent similar items in the following figures. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. In addition, the terms "first", "second", "third", etc. are only used to distinguish the description and are not to be understood as indicating or implying relative importance.

Finally, it should be noted that the above-described embodiments are only specific implementation methods of the present application, which are used to illustrate the technical solutions of the present application, rather than to limit them. The protection scope of the present application is not limited thereto. Although the present application is described in detail with reference to the above-mentioned embodiments, ordinary technicians in the field should understand that any technician familiar with the technical field can still modify the technical solutions recorded in the above-mentioned embodiments within the technical scope disclosed in the present application, or can easily think of changes, or make equivalent replacements for some of the technical features therein; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application. They should all be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.

Claims (12)

1. A call information processing method, characterized in that it is applied to a data answering device, the method comprising: Determine, according to the operation type input by the user, a template to be spliced corresponding to the operation type, wherein the template to be spliced includes: at least one template string and a variable string; Acquire the template voice corresponding to the template character string, and acquire the target data corresponding to the variable character string from the real-time data storage device according to the identifier of the operation object input by the user, wherein the template voice is pre-stored in the data response device; Determine the target data voice of the target data according to the target data and the current voice database, the current voice database is dynamically updated by the voice updating device and sent to the data response device; Generate and output the operation result of the operation object according to the template voice and the target data voice; Determining the target data voice of the target data according to the target data and the current voice database includes: The target data voice corresponding to the target data is searched from the current voice database, wherein the current voice database stores the following contents: numbers and voice files corresponding to the numbers, names of operation objects and voice files corresponding to the names of operation objects, text information of operation objects and voice files corresponding to the text information. 2. The method according to claim 1, characterized in that the process of the voice updating device dynamically updating the current voice database comprises: Acquire a current data file based on a preset period, and determine whether the current voice database needs to be updated according to the current data file; If so, the current voice database is updated according to the current data file to obtain an updated current voice database, and the updated current voice database is sent to each of the data response devices. 3. The method according to claim 2, characterized in that the step of determining whether the current voice database needs to be updated according to the current data file comprises: Comparing the current data file with the data file of the current voice database to determine whether the current data file is the same as the data file of the current voice database; If they are the same, the current voice database needs to be updated; if they are not the same, the current voice database does not need to be updated. 4. The method according to claim 3, characterized in that the updating process of the current voice database according to the current data file to obtain the updated current voice database comprises: Determine at least one update data according to the current data file and the data file of the current voice database; Sending the at least one updated data to a voice conversion device to obtain voice information of each updated data; The current voice database is updated according to the voice information of each update data to obtain the updated current voice database. 5. The method according to claim 2, characterized in that the step of sending the updated current voice database to each of the data response devices comprises: Determining at least one data response device to be updated according to a pre-stored data response device list and an activation state of each of the data response devices; The updated current voice database is sent to each of the data response devices to be updated. 6. The method according to claim 1, characterized in that the step of obtaining the template speech corresponding to the template character string comprises: The template speech corresponding to the template character string is searched from a template speech library, wherein the template speech library includes: a plurality of template character strings and speech information corresponding to each template character string. 7. The method according to claim 1, characterized in that the step of obtaining the target data corresponding to the variable character string from a real-time data storage device according to the identifier of the operation object input by the user comprises: Searching the real-time data storage device for the selected data corresponding to the identifier of the operation object; Arrange the selected data in the order of the variable character strings to obtain the target data. 8. The method according to claim 1, wherein the target data is the value of the variable string; The step of generating and outputting the operation result of the operation object according to the template voice and the target data voice includes: The template voice is filled into the position corresponding to the template character string, and the target data voice is filled into the position corresponding to the variable character string to obtain the operation result of the operation object. 9. A data response device, comprising: A first determination module is used to determine, according to an operation type input by a user, a template to be spliced corresponding to the operation type, wherein the template to be spliced includes: at least one template string and a variable string; An acquisition module, used to acquire the template voice corresponding to the template character string, and acquire the target data corresponding to the variable character string from the real-time data storage device according to the identifier of the operation object input by the user, wherein the template voice is pre-stored in the data response device; A second determination module, for determining the target data voice of the target data according to the target data and a current voice database, wherein the current voice database is dynamically updated by a voice updating device and sent to the data response device; A generating module, used for generating and outputting the operation result of the operation object according to the template voice and the target data voice; The second determining module is used to: The target data voice corresponding to the target data is searched from the current voice database, wherein the current voice database stores the following contents: numbers and voice files corresponding to the numbers, names of operation objects and voice files corresponding to the names of operation objects, text information of operation objects and voice files corresponding to the text information. 10. A call information processing system, characterized in that it comprises a data answering device, a real-time data storage device, a voice updating device and a voice conversion device in the call information processing method according to any one of claims 1 to 8. 11. An electronic device, characterized in that it comprises: a processor, a storage medium and a bus, wherein the storage medium stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor communicates with the storage medium through the bus, and the processor executes the machine-readable instructions to perform the steps of a call information processing method as described in any one of claims 1 to 8. 12. A computer-readable storage medium, characterized in that a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the steps of the call information processing method according to any one of claims 1 to 8 are executed.