CN115659994B

CN115659994B - Data processing method and related device in human-computer interaction system

Info

Publication number: CN115659994B
Application number: CN202211577774.1A
Authority: CN
Inventors: 杨强; 龙方舟
Original assignee: Shenzhen Renma Interactive Technology Co Ltd
Current assignee: Shenzhen Renma Interactive Technology Co Ltd
Priority date: 2022-12-09
Filing date: 2022-12-09
Publication date: 2023-03-03
Anticipated expiration: 2042-12-09
Also published as: CN115659994A

Abstract

The embodiment of the application discloses a data processing method and a related device in a man-machine interaction system, wherein the method comprises the following steps: the server acquires a first user input statement, analyzes the first user input statement to obtain a first semantic recognition result, and matches with the adaptive first service man-machine conversation engine; the server also obtains a second user input statement from the terminal equipment, analyzes the second user input statement to obtain a second semantic recognition result, judges whether the first business man-machine conversation engine can process the second user input statement or not, and receives and processes the second user input statement by the first business man-machine conversation engine if the first business man-machine conversation engine can process the second user input statement; and if not, determining a second business man-machine conversation engine for processing the input sentence of the second user through the general man-machine conversation engine, judging whether a data bearing relation exists between the second business man-machine conversation engine and the first business man-machine conversation engine, and if so, migrating the first process data stored in the first business man-machine conversation engine to the second business man-machine conversation engine. The method and the device are beneficial to improving the human-computer interaction effect.

Description

Data processing method in human-computer interaction system and related device

Technical Field

The application relates to the technical field of general data processing in the Internet industry, in particular to a data processing method and a related device in a man-machine interaction system.

Background

Currently, in the field of human-computer interaction, a user input statement related to a certain service field can only be processed by a service human-computer interaction engine corresponding to the service field, and switching a service corresponding to the user input statement calls a different human-computer interaction engine to process the service. However, after the service is switched, the accuracy and intelligence of subsequent response to multiple rounds of conversations are affected by the subsequent man-machine conversation engine due to the missing of the previous interaction information.

Disclosure of Invention

The embodiment of the application provides a data processing method and a related device in a man-machine interaction system, aiming at improving the man-machine interaction effect.

In a first aspect, an embodiment of the present application provides a data processing method in a human-computer interaction system, which is applied to a server in the human-computer interaction system, where the human-computer interaction system includes the server and a terminal device used by a user for performing a human-computer conversation, the server is deployed with a general human-computer conversation engine and multiple business human-computer conversation engines used for supporting multiple types of different business functions, and the business functions supported by any two human-computer conversation engines are different from each other; the method comprises the following steps:

acquiring a first user input sentence from the terminal equipment;

determining, by the universal human machine dialog engine, a first semantic recognition result of the first user input sentence and determining a first business human machine dialog engine that fits the first semantic recognition result;

calling the first user input statement through the first service man-machine conversation engine, processing the first user input statement to obtain a first processing result, and sending the first processing result to the terminal equipment;

in the same continuous conversation process, acquiring a second user input statement from the terminal equipment;

determining a second semantic recognition result of the second user input statement through the general man-machine conversation engine, and judging whether the first business man-machine conversation engine can process the second user input statement;

if the processing is available, calling the second user input statement through the first service man-machine conversation engine, and processing the second user input statement to obtain a second processing result;

if the processing is impossible, determining a second business man-machine conversation engine adapted to the second semantic recognition result through the general man-machine conversation engine, and judging whether a data bearing relation exists between the first business man-machine conversation engine and the second business man-machine conversation engine, wherein the data bearing relation means that first process data generated by the first business man-machine conversation engine in a first man-machine conversation process comprises characteristic data required by the second business man-machine conversation engine in the second man-machine conversation process;

if so, sending a data migration instruction to the first service man-machine conversation engine through the general man-machine conversation engine, wherein the data migration instruction is used for indicating the first service man-machine conversation engine to transmit the first process data to the second service man-machine conversation engine;

receiving the data migration instruction through the first service man-machine conversation engine, and responding to the data migration instruction to complete data migration operation aiming at the first process data;

receiving the first process data through the second service man-machine conversation engine, processing the second user input statement according to the first process data to obtain a third processing result, and sending the third processing result to the terminal equipment;

and if not, receiving a second user input statement from the general man-machine conversation engine through the second business man-machine conversation engine, and processing the second user input statement to obtain a fourth processing result.

In a second aspect, an embodiment of the present application provides a data processing apparatus in a human-computer interaction system, which is applied to a server in the human-computer interaction system, where the human-computer interaction system includes the server and a terminal device used by a user for performing a human-computer conversation, the server is deployed with a general human-computer conversation engine and multiple business human-computer conversation engines used for supporting multiple types of different business functions, and the business functions supported by any two human-computer conversation engines are different from each other; the device comprises:

an acquisition unit configured to acquire a first user input sentence from the terminal device;

the acquisition unit is further used for acquiring a second user input statement from the terminal equipment in the same continuous conversation process;

a processing unit for determining a first semantic recognition result of the first user input sentence and determining a first business man-machine dialogue engine adapted to the first semantic recognition result by the general man-machine dialogue engine;

the processing unit is further configured to invoke the first user input statement through the first service human-computer dialog engine, process the first user input statement to obtain a first processing result, and send the first processing result to the terminal device;

the processing unit is further configured to determine a second semantic recognition result of the second user input sentence through the general man-machine conversation engine, and determine whether the first business man-machine conversation engine can process the second user input sentence;

the processing unit is further configured to receive the data migration instruction through the first service man-machine conversation engine, and complete a data migration operation for the first process data in response to the data migration instruction;

the processing unit is further configured to receive the first process data through the second service man-machine conversation engine, process the second user input statement according to the first process data to obtain a third processing result, and send the third processing result to the terminal device;

In a third aspect, embodiments of the present application provide a server comprising a processor, a memory, a communication interface, and one or more programs stored in the memory and configured to be executed by the processor, the programs including instructions for performing the steps in the first aspect of embodiments of the present application.

In a fourth aspect, an embodiment of the present application provides a computer storage medium storing a computer program for electronic data exchange, where the computer program makes a computer perform part or all of the steps described in the first aspect of the embodiment.

It can be seen that, in this example, the server may first obtain a first user input sentence from the terminal device, and determine, through the universal human-machine dialog engine, a first semantic recognition result of the first user input sentence, and determine a first business human-machine dialog engine adapted to the first semantic recognition result; and then, receiving a first user input statement from the universal man-machine conversation engine through the first service man-machine conversation engine, processing the first user input statement to obtain a first processing result, and sending the first processing result to the terminal equipment. In the same continuous conversation process, the server can also obtain a second user input statement from the terminal equipment, determine a second semantic recognition result of the second user input statement through the universal man-machine conversation engine, and judge whether the first service man-machine conversation engine can process the second semantic recognition result; if the processing is available, receiving a second user input statement from the universal man-machine conversation engine through the first service man-machine conversation engine, and processing the second user input statement; if the processing is impossible, determining a second service man-machine conversation engine adapted to a second semantic recognition result through the general man-machine conversation engine, and judging whether a data bearing relation exists between the first service man-machine conversation engine and the second service man-machine conversation engine, wherein the data bearing relation means that first process data generated by the first service man-machine conversation engine in a first man-machine conversation process contains characteristic data required by the second service man-machine conversation engine in the second man-machine conversation process; if the data bearing relation exists, sending a data migration instruction to a first service man-machine conversation engine through a general man-machine conversation engine, wherein the data migration instruction is used for indicating the first service man-machine conversation engine to transmit first process data to a second service man-machine conversation engine; receiving a data migration instruction through a first service man-machine conversation engine, and responding the data migration instruction through the first service man-machine conversation engine to complete data migration operation aiming at first process data; then, receiving the first process data by a second service man-machine conversation engine, processing the second user input statement according to the first process data to obtain a second processing result, and sending the second processing result to the terminal equipment; and if the data bearing relation does not exist, the server receives a second user input statement from the general man-machine conversation engine through the second business man-machine conversation engine and processes the second user input statement.

Therefore, when the server acquires the second user input statement, if the service man-machine conversation engine needs to be updated, the server can send a data migration instruction to the first service man-machine conversation engine through the general man-machine conversation engine, so that the first service man-machine conversation engine migrates the first process data to the second service man-machine conversation engine according to the data migration instruction, the second service man-machine conversation engine can be prevented from losing the process data of previous turn conversation in the continuous conversation process, the accuracy of the second service man-machine conversation engine in responding to the first user input statement can be improved, and the intelligent interaction effect of the man-machine interaction system can be improved.

Drawings

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings used in the embodiments or the prior art descriptions will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative efforts.

Fig. 1 is a schematic architecture diagram of a human-computer interaction system according to an embodiment of the present application;

fig. 2 is a diagram illustrating an exemplary composition of a server according to an embodiment of the present disclosure;

fig. 3 is a schematic flowchart of a data processing method in a human-computer interaction system according to an embodiment of the present application;

FIG. 4 is a block diagram illustrating functional units of a data processing apparatus in a human-computer interaction system according to an embodiment of the present disclosure;

fig. 5 is a block diagram illustrating functional units of a data processing apparatus in another human-computer interaction system according to an embodiment of the present disclosure.

Detailed Description

In order to make the technical solutions of the present application better understood by those skilled in the art, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all the embodiments. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments in the present application without making any creative effort belong to the protection scope of the present application.

The terms "first," "second," and the like in the description and claims of the present application and in the above-described drawings are used for distinguishing between different objects and not for describing a particular order. Furthermore, the terms "include" and "have," as well as any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those steps or elements listed, but may alternatively include other steps or elements not listed, or inherent to such process, method, article, or apparatus.

Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the application. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. It is explicitly and implicitly understood by one skilled in the art that the embodiments described herein may be combined with other embodiments.

The embodiments of the present application will be described below with reference to the accompanying drawings.

The technical solution of the present application can be applied to a human-computer interaction system 10 as shown in fig. 1, where the human-computer interaction system 10 includes a server 100 and a terminal device 200.

The server 100 in the present application may be configured as shown in fig. 2, and the server 100 may include a processor 110, a memory 120, a communication interface 130, and one or more programs 121, where the one or more programs 121 are stored in the memory 120 and configured to be executed by the processor 110, and the one or more programs 121 include instructions for executing any step of the method embodiments described below.

The communication interface 130 is used to support communication between the server 100 and other devices. The processor 110 may be, for example, a Central Processing Unit (CPU), a general purpose processor, a Digital Signal Processor (DSP), an Application-specific integrated circuit (ASIC), a Field Programmable Gate Array (FPGA) or other programmable logic device, transistor logic, hardware components, or any combination thereof. Which may implement or perform the various illustrative logical blocks, units, and circuits described in connection with the disclosure of the embodiments of the application. The processor may also be a combination of computing functions, e.g., comprising one or more microprocessors, DSPs, and microprocessors, among others.

The memory 120 may be either volatile memory or nonvolatile memory, or may include both volatile and nonvolatile memory. The non-volatile memory may be a read-only memory (ROM), a Programmable ROM (PROM), an Erasable PROM (EPROM), an Electrically Erasable PROM (EEPROM), or a flash memory. Volatile memory can be Random Access Memory (RAM), which acts as external cache memory. By way of example, but not limitation, many forms of Random Access Memory (RAM) are available, such as Static RAM (SRAM), dynamic Random Access Memory (DRAM), synchronous Dynamic Random Access Memory (SDRAM), SDRAM (SDRAM), ddr (double data rate) SDRAM, edraws (DDRSDRAM), enhanced SDRAM (enhanced SDRAM, ESDRAM), SDRAM (synchronous DRAM), SDRAM (SLDRAM), and rdram (DRRAM).

In particular implementations, the processor 110 is configured to perform any one of the steps performed by the first server or in the method embodiments described below, and when performing data transmission, such as sending, optionally invokes the communication interface 130 to perform the corresponding operation.

It should be noted that the structural diagram of the server 100 is only an example, and the number of the specifically included devices may be more or less, and is not limited herein.

Referring to fig. 3, fig. 3 is a schematic flowchart of a data processing method in a human-computer interaction system according to an embodiment of the present application, where the method may be applied to a server 100 in the human-computer interaction system 10 shown in fig. 1, where the human-computer interaction system 10 includes the server 100 and a terminal device 200 used by a user for performing a human-computer conversation, the server 100 is deployed with a general human-computer conversation engine and multiple business human-computer conversation engines for supporting multiple types of different business functions, and business functions supported by any two human-computer conversation engines are different from each other.

The universal man-machine conversation engine is used for performing conventional semantic recognition, performing service function skipping, responding to functional conversations without specific service function directivity and the like. The business human-machine dialogue engine is mainly used for responding to functional dialogue of specific certain personal business functions.

As shown in fig. 3, the data processing method in the human-computer interaction system includes:

s201, acquiring a first user input statement from the terminal equipment.

The terminal device can be an intelligent device which can perform human-computer interaction with a user, such as a smart phone, a smart tablet, a smart wearable device and a vehicle-mounted device.

The first user input statement is voice information collected by the terminal device.

Specifically, after the terminal device collects the first user input sentence, the first user input sentence may be uploaded to the server, so that the server processes the first user input sentence. For example, if the sentence of the interaction between the user and the terminal device is "help me to set two movie tickets near mall a", the audio information collected by the terminal device is "help me to set two movie tickets near mall a", that is, the first user input sentence uploaded to the server by the terminal device is "help me to set two movie tickets near mall a".

S202, determining a first semantic recognition result of the first user input statement through a general man-machine conversation engine, and determining a first business man-machine conversation engine which is adaptive to the first semantic recognition result.

In specific implementation, a first user input statement is converted into text information, then a first semantic recognition result corresponding to the first user input statement is recognized by the universal man-machine conversation engine through methods of statement analysis, keyword extraction and the like, an intention corresponding to the first user input statement is obtained, and a first business man-machine conversation engine is determined according to the first semantic recognition result.

Specifically, the universal man-machine conversation engine stores a service form, the service form includes service table entries corresponding to service functions that can be processed by each service man-machine conversation engine, and service keywords associated with a service are stored in the service table entries (i.e., the service keywords associated with the service are values of the service table entries). After the general man-machine conversation engine acquires the text information corresponding to the first user input sentence, the text information can be analyzed to obtain a first semantic recognition result, and the first semantic recognition result comprises words used for representing the processing intention corresponding to the business function. The general man-machine conversation engine can match the first semantic recognition result with the service key words in the service form, so as to determine the service table item adapted to the first semantic recognition result, and further determine the first service man-machine conversation engine according to the service table item.

For example, if the first semantic recognition result is the requirement information about ordering high-speed railway tickets, the universal human-computer interaction engine may match the word "order high-speed railway tickets" with the service form, so as to obtain a service keyword "order high-speed railway tickets" adapted to the word in the service form, and further determine the service human-computer interaction engine corresponding to the service keyword "order high-speed railway tickets" as the first human-computer interaction engine.

S203, the first user input statement is called through the first service man-machine conversation engine, the first user input statement is processed to obtain a first processing result, and the first processing result is sent to the terminal device.

In a specific implementation, after the universal man-machine conversation engine determines the first service man-machine conversation engine, the first service man-machine conversation engine may be activated, and the first service man-machine conversation engine may obtain the first user input sentence, so as to process the first user input sentence, and obtain the first processing result. The first processing result is a business processing result aiming at the first user input statement. The first service man-machine conversation engine can send a first response message carrying the first processing result to the terminal device to instruct the terminal device to play the first processing result so as to respond to the first user input sentence input by the user.

Illustratively, if the first user input statement is: help me to order a high-speed railway ticket which starts about 2 pm today and goes from city A to city B. At this point, the first business man-machine conversation engine can be confirmed to be the man-machine conversation engine for processing the high-speed railway ticket business. When the first human-machine dialog engine receives the first user input statement, the first user input statement can be processed, and a first processing result is obtained, wherein the first processing result is ticket purchasing information. For example, the first processing result may be: having ordered a high railway ticket that departed from the west station in city a at 2 pm 10 minutes today, the train will arrive at the north station in city B at 2 pm 43 minutes today.

And S204, acquiring a second user input statement from the terminal equipment in the same continuous conversation process.

The manner of acquiring the second user input sentence may refer to step S201, and is not further described here.

S205, determining a second semantic recognition result of the second user input statement through the general man-machine conversation engine, and judging whether the first business man-machine conversation engine can process the second user input statement.

The process of determining the second semantic identification result of the second user input sentence by the universal human-computer interaction engine may refer to step S202, which is not described in detail herein.

In specific implementation, after the server analyzes the second semantic recognition result, the server compares the second semantic recognition result with the service table entry corresponding to the first service man-machine conversation engine in the service table and judges whether the second semantic recognition result is adaptive to the service table entry. If it is adapted, it means that the first business human machine dialog engine can process the second user input sentence, and the following step S206 can be executed. If not, it means that the first business human machine dialog engine cannot process the second user input sentence, and the following steps S207 to S211 can be performed.

And S206, if the processing is available, calling the second user input statement through the first service man-machine conversation engine, and processing the second user input statement to obtain a second processing result.

The process of the first business human-computer interaction engine processing the second user input sentence can refer to the step S203, and is not further described here. At this time, the first service man-machine conversation engine may send a second response message carrying the second processing result to the terminal device to instruct the terminal device to play the second processing result, so as to respond to the second user input sentence input by the user.

And S207, if the processing cannot be performed, determining a second service man-machine conversation engine adapted to the second semantic recognition result through the general man-machine conversation engine, and judging whether a data bearing relation exists between the first service man-machine conversation engine and the second service man-machine conversation engine, wherein the data bearing relation means that first process data generated by the first service man-machine conversation engine in a first man-machine conversation process contains characteristic data required by the second service man-machine conversation engine in a second man-machine conversation process.

In a specific implementation, when the first business man-machine conversation engine cannot process a sentence input by a second user, the general man-machine conversation engine may match a business table entry adapted to the second semantic recognition result in the business table, and determine the business man-machine conversation engine corresponding to the business table entry as the second business man-machine conversation engine.

In a specific implementation, the universal human-machine conversation engine further needs to determine whether a data receiving relationship exists between the first service human-machine conversation engine and the second service human-machine conversation engine, if so, the following steps S208 to S210 are executed, and if not, the following step S211 is executed.

Specifically, each business man-machine conversation engine is provided with a corresponding form, each form comprises a plurality of form items, the business man-machine conversation engine can store information corresponding to the form items in man-machine conversation according to the corresponding relation between the user input statements and the form items, and data stored by the business man-machine conversation engine is the value of the form items. The universal man-machine conversation engine can store preset corresponding relations among form items in forms of different business man-machine conversation engines. When the universal man-machine conversation engine judges whether a data bearing relationship exists between the first service man-machine conversation engine and the second service man-machine conversation engine, whether the data bearing relationship exists can be judged according to whether a form item in a form of the first service man-machine conversation engine, which stores data (namely first process data), and a form item in a form of the second service man-machine conversation engine have a preset corresponding relationship. The preset corresponding relationship may be whether the form items of different business man-machine conversation engines are the same type of content, for example, the form items include time types, location types, character types, and the like.

And S208, if so, sending a data migration instruction to the first service man-machine conversation engine through the general man-machine conversation engine, wherein the data migration instruction is used for indicating the first service man-machine conversation engine to transmit the first process data to the second service man-machine conversation engine.

In a specific implementation, when the first service man-machine conversation engine transmits the first process data to the second service man-machine conversation engine according to the data migration instruction, the first process data can be directly sent to the second service man-machine conversation engine by the first service man-machine conversation engine, so that the data transmission efficiency is improved. Or, the first service man-machine conversation engine may send the first process data to the general man-machine conversation engine, and then the general man-machine conversation engine sends the first process data to the second service man-machine conversation engine, so as to implement data isolation between the service man-machine conversation engines and avoid mutual interference.

S209, receiving the data migration instruction through the first business man-machine conversation engine, and responding to the data migration instruction to complete the data migration operation aiming at the first process data.

S210, receiving the first process data through the second business man-machine conversation engine, processing the second user input statement according to the first process data to obtain a third processing result, and sending the third processing result to the terminal equipment.

In specific implementation, after receiving the first process data, the second service man-machine conversation engine can process the second user input statement according to the first process number, so as to obtain a third processing result. The processing procedure can refer to the above step S203, and will not be further described here. The second service man-machine conversation engine can also send a third response message carrying the third processing result to the terminal equipment to instruct the terminal equipment to play the third processing result, so as to respond to a second user input statement input by the user.

And S211, if not, receiving a second user input statement from the general man-machine conversation engine through the second business man-machine conversation engine, and processing the second user input statement to obtain a fourth processing result.

If no data bearing relation exists between the first service man-machine conversation engine and the second service man-machine conversation engine, the second service man-machine conversation engine can directly call the second user input statement and process the second user input statement, and therefore a fourth processing result is obtained. And a fourth response message carrying the fourth processing result may be sent to the terminal device to instruct the terminal device to play the fourth processing result, so as to respond to the second user input statement input by the user.

It can be seen that, in this example, the server may first obtain a first user input sentence from the terminal device, and determine, through the universal man-machine dialog engine, a first semantic recognition result of the first user input sentence, and determine a first business man-machine dialog engine adapted to the first semantic recognition result; and then, receiving a first user input statement from the universal man-machine conversation engine through the first service man-machine conversation engine, processing the first user input statement to obtain a first processing result, and sending the first processing result to the terminal equipment. In the same continuous conversation process, the server can also obtain a second user input statement from the terminal equipment, determine a second semantic recognition result of the second user input statement through the universal man-machine conversation engine, and judge whether the first service man-machine conversation engine can process the second semantic recognition result; if the processing is available, receiving a second user input statement from the general man-machine conversation engine through the first business man-machine conversation engine, and processing the second user input statement; if the processing is impossible, determining a second service man-machine conversation engine adapted to a second semantic recognition result through the general man-machine conversation engine, and judging whether a data bearing relation exists between the first service man-machine conversation engine and the second service man-machine conversation engine, wherein the data bearing relation means that first process data generated by the first service man-machine conversation engine in a first man-machine conversation process contains characteristic data required by the second service man-machine conversation engine in a second man-machine conversation process; if the data connection relation exists, sending a data migration instruction to a first service man-machine conversation engine through a general man-machine conversation engine, wherein the data migration instruction is used for indicating the first service man-machine conversation engine to transmit first process data to a second service man-machine conversation engine; receiving a data migration instruction through the first service man-machine conversation engine, and responding the data migration instruction through the first service man-machine conversation engine to complete data migration operation aiming at the first process data; then, receiving the first process data by a second service man-machine conversation engine, processing a second user input statement according to the first process data to obtain a second processing result, and sending the second processing result to the terminal equipment; and if the data bearing relation does not exist, the server receives a second user input statement from the general man-machine conversation engine through the second service man-machine conversation engine and processes the second user input statement. Therefore, when the server acquires the second user input statement, if the service man-machine conversation engine needs to be updated, the server can send a data migration instruction to the first service man-machine conversation engine through the general man-machine conversation engine, so that the first service man-machine conversation engine migrates the first process data to the second service man-machine conversation engine according to the data migration instruction, the second service man-machine conversation engine can be prevented from losing the process data of previous turn conversation in the continuous conversation process, the accuracy of the second service man-machine conversation engine in responding to the first user input statement can be improved, and the intelligent interaction effect of the man-machine interaction system can be improved.

In one possible example, the receiving, by the first business human machine dialog engine, the data migration instruction and completing, in response to the data migration instruction, a data migration operation for the first process data includes: sending, by the first business human machine dialog engine, the first process data to the general human machine dialog engine; and receiving the first process data through the general man-machine conversation engine, processing the first process data according to a preset data receiving conversion rule to obtain target data, and sending the target data to the second business man-machine conversation engine.

The preset data receiving and converting rule is a rule for converting the first process data into feature data required by a second business man-machine conversation engine for performing second man-machine conversation. Specifically, the preset data receiving and converting rule is configured according to the incidence relation of the form items in the forms of the first service man-machine conversation engine and the second service man-machine conversation engine.

In the specific implementation, after receiving a data migration instruction, a first business man-machine conversation engine sends first process data to a general man-machine conversation engine, after receiving the first process data, the general man-machine conversation engine determines a preset data receiving conversion rule corresponding to the data receiving relationship according to an incidence relation between the first business man-machine conversation engine and a second business man-machine conversation engine, the general man-machine conversation engine converts the first process data into feature data (namely target data) required by the second business man-machine conversation engine when processing a second user input statement according to the preset data receiving conversion rule, and then the general man-machine conversation engine sends the target data to the second business man-machine conversation engine, so that the second business man-machine conversation engine can process the second user input statement according to the target data.

As can be seen, in this example, the general man-machine conversation engine converts the first process data into the target data according to the preset data receiving conversion rule, and then sends the target data to the second service man-machine conversation engine, so that not only can data isolation between the first service man-machine conversation engine and the second service man-machine conversation engine be achieved, mutual interference be avoided, but also the processing pressure of the second service man-machine conversation engine can be reduced, so that the second service man-machine conversation engine can better perform processing operation for service functions, and the reliability of the third processing result is improved.

In one possible example, the sending, by the first business human machine dialog engine to the general human machine dialog engine, the first process data includes: storing first key information in first process data through the first business man-machine conversation engine according to a first form, wherein the first form is a form corresponding to the first business man-machine conversation engine and comprises a plurality of form items, and the first key information is data corresponding to the form items of the first form in the first process data; and sending the first key information to the general man-machine conversation engine through the first business man-machine conversation engine.

The first key information is the value of a form item in a first form stored by a first business man-machine conversation engine.

In a specific implementation, data stored in a form item in a first form of a first business man-machine conversation engine is first key information in a first semantic recognition result, and the first key information is a keyword corresponding to the form item, extracted from a first user input sentence and a corresponding processing result by the first business man-machine conversation engine. The first process data transmitted to the general man-machine conversation engine by the first business man-machine conversation engine is the first key information.

Illustratively, if the first user input statement is: ordering a high-speed railway ticket from city A to city B which starts at about 2 pm today. The first processing result corresponding to the first input sentence is: having ordered a high iron ticket that departs from the west station in city a at 10 pm 2 pm today, the train will arrive at the north station in city B at 43 pm today. The information is first process data generated by the first business man-machine conversation engine through first man-machine conversation aiming at the first user input statement. The first business man-machine conversation engine can extract data respectively corresponding to the form items of the starting time, the ending time, the starting place and the destination from the first process data, such as the starting time: point 2, 10 minutes, end time: point 2, 43 min, initially: a west station, destination: north station city B. The first business human machine dialogue engine can store the data in the first form and send the data to the general human machine dialogue engine when data migration is needed.

As can be seen, in this example, by transmitting the first key information in the first process data, it can be ensured that the second service man-machine conversation engine can receive the feature data useful for processing the second user input statement in the previous turn of the conversation in the current continuous conversation process, and the amount of transmitted data can be reduced, the data transmission efficiency is improved, and the storage pressure is reduced. Moreover, compared with the transmission of complete first process data, the transmission of the first key information can also reduce the process of data extraction by the second business man-machine conversation engine, and improve the processing efficiency of the second business man-machine conversation engine.

In one possible example, the processing the first process data according to a preset data receiving and converting rule to obtain target data includes: acquiring a first form of the first service man-machine conversation engine and a second form of the second service man-machine conversation engine through the general man-machine conversation engine, wherein the second form is a form corresponding to the second service man-machine conversation engine; determining an incidence relation between a form item corresponding to the first key information in the first form and a form item of the second form through the general man-machine conversation engine, and determining a corresponding preset data carrying conversion rule according to the incidence relation, wherein the incidence relation is at least one of a time incidence relation, a place incidence relation and a person incidence relation; and processing the first key information according to the preset data carrying conversion rule through the universal man-machine conversation engine to obtain the target data.

And the preset data carrying conversion rule corresponds to the association relation. Namely, the preset corresponding association relationship of the carrying conversion rule comprises at least one of a time conversion rule, a place conversion rule and a person conversion rule.

In specific implementation, after receiving the first key information, the universal human-computer interaction engine may first obtain a first form of the first business human-computer interaction engine and a second form of the second business human-computer interaction engine, determine a form item of the first form and a form item of the second form, and then determine at least one association relationship between the form item of the second form and the form item in which the first key information is stored (the form item in which the first key information is stored refers to a form item having a value in the first form) by combining the second semantic recognition result. And then determining a preset data carrying conversion rule corresponding to the association relation, processing the first key information according to the corresponding preset data carrying conversion rule to obtain target data, and transmitting the target data to a second business man-machine conversation engine.

Specifically, the time association refers to a chronological order of events corresponding to two human-computer conversations in the same continuous conversation process. The generic human-machine dialog engine may determine the type of association from the form items of the first form and the form items of the second form. And if the incidence relation comprises a time incidence relation, the universal man-machine conversation engine determines a preset data carrying conversion rule by combining a second semantic analysis result. Specifically, if it is known from the second semantic parsing result that the event corresponding to the second user input statement is located after the event corresponding to the first user input statement occurs, it may be determined that the preset data receiving conversion rule is to convert the end time in the first key information into the start time required for processing the second user input statement. If the event corresponding to the second user input statement is located before the event corresponding to the first user input statement occurs according to the second semantic parsing result, the preset data receiving conversion rule can be determined to convert the start time in the first key information into the end time required for processing the second user input statement. For example, if the first user input statement is "help me order high-speed railway tickets that are open to tomorrow afternoon to city C", then the corresponding form items of the first form and their values may be known to include "start: city D (current location) south station, destination: c north station, start time: tomorrow afternoon, two points, and the end time: tomorrow afternoon, four-point, etc. If the second user input statement is "offer me car to market a again". At this time, the universal man-machine conversation engine can judge that the first man-machine conversation engine and the second man-machine conversation engine have a time association relationship, and the event corresponding to the first user input statement occurs before the event corresponding to the second user input statement, so that the target data "start time" for realizing the second user input statement can be obtained: four afternoons tomorrow ", i.e., the start time of taxi-taking should be four afternoons tomorrow.

Specifically, the location association relationship refers to an association relationship between a starting location and a destination location of an event corresponding to two human-computer conversations in the same continuous conversation process. The generic human-machine dialog engine may determine the type of association from the form items of the first form and the form items of the second form. And if the incidence relation comprises a place incidence relation, the universal man-machine conversation engine determines a preset data carrying conversion rule by combining a second semantic analysis result. Specifically, if it is known from the second semantic analysis result that the event corresponding to the second user input statement occurs after the event corresponding to the first user input statement, it may be determined that the preset data receiving and converting rule is to convert the destination in the first key information into the start place required for processing the second user input statement. If the event corresponding to the second user input statement occurs before the event corresponding to the first user input statement according to the second semantic parsing result, it may be determined that the preset data receiving conversion rule is to convert the start in the first key information into the destination required for processing the second user input statement. For example, if the first user input statement is "help me book a high-speed railway from tomorrow afternoon to city C", then the corresponding form items of the first form and their values may be found according to the booking information, including "start: city D (current location) south station, destination: c north station, start time: two points in the afternoon of tomorrow, ending time: tomorrow afternoon, four-point, etc. If the second user input statement is "vehicle to market a after helping me". At this time, the general man-machine conversation engine can judge that the first man-machine conversation engine and the second man-machine conversation engine have a place incidence relation, and the event corresponding to the first user input sentence occurs before the event corresponding to the second user input sentence, so that target data "an initial place: north station C, i.e., the origin of the taxi taking, should be north station C.

Specifically, the person association relationship refers to an association relationship between event executors corresponding to two human-computer conversations in the same continuous conversation process. The generic human-machine dialog engine may determine the type of association from the form items of the first form and the form items of the second form. And if the incidence relation comprises a character incidence relation, the universal man-machine conversation engine determines a preset data carrying conversion rule by combining a second semantic analysis result. Specifically, if it is known that the event executor is not changed according to the second semantic analysis result, the preset data receiving conversion rule is that the event executor in the first key information is determined as the event executor corresponding to the second user input statement. If the event executor is known to be changed according to the second semantic analysis result, the preset data receiving conversion rule is to obtain an event executor corresponding to the second user input statement according to the second semantic recognition result and the event executor analysis in the first key information. For example, if the first user input sentence is "help me, zhang san, lie si, wang wu order high-speed railway tickets from tomorrow to city C", then the corresponding form items of the first form and their values may be known according to the ticket ordering information, including "start: city D (current location) south station, destination: c north station, start time: tomorrow afternoon, two points, end time: four afternoon tomorrow, the event executor: currently, users, zhang three, li four and Wang five. If the second user inputs a sentence "help the vehicle in the market A after the third user reaches, help the rest people to decide the vehicle in the office building B". The universal man-machine conversation engine can judge that the first man-machine conversation engine and the second man-machine conversation engine have a character incidence relation, the time executor changes, the universal man-machine conversation engine can determine the number of the first executor (namely the executor who executes the taxi to go to the market A) according to the second semantic recognition result, and determine the number of the second executor to be the current user, the number of the fourth Li and the number of the fifth Wang according to the second semantic recognition result and the first key information, namely the target data comprises the first executor and the second executor.

In specific implementation, the universal man-machine conversation engine can sequentially judge whether the time incidence relation, the place incidence relation and the figure incidence relation exist, so that data omission is avoided. Specifically, the order of determination of the time association relationship, the place association relationship, and the person association relationship may be set arbitrarily.

As can be seen, in this example, the first key information migrated by the first business human-machine dialog engine is converted into the target data by the general human-machine dialog engine, so that the second business human-machine dialog engine can directly utilize the target data for processing when performing the second human-machine dialog for the second user input sentence, and the target data does not need to be processed again, which can reduce the processing pressure of the second business human-machine dialog engine, improve the processing efficiency of the second business human-machine dialog engine, so that the second business human-machine dialog engine can better perform processing operations for business functions, and improve the reliability of the third processing result.

In one possible example, after the determining whether a data connection relationship exists between the first service human-machine conversation engine and the second service human-machine conversation engine, the method further includes: and if the first state switching instruction exists, sending a first state switching instruction to the first service man-machine conversation engine, wherein the first state switching instruction is used for indicating the first service man-machine conversation engine to be switched from an activated state to a standby state.

The service man-machine conversation engine comprises three states of standby, activation and to-be-activated, and can be switched among the three states according to a state switching instruction from the general man-machine conversation engine. Wherein the active state is for the business human machine dialog engine currently in use. The standby state may be for a business human machine dialog engine that was used (i.e., activated) during a continuous dialog process, and during a previous dialog process. The to-be-activated state is for all the business man-machine conversation engines which are not activated.

The business man-machine conversation engine in the standby state cannot clear process data generated by man-machine conversation. The service man-machine conversation engine in the state to be activated does not store any man-machine interaction data. The activated business man-machine conversation engine stores the process data generated by man-machine conversation.

In a specific implementation, if there is no data carrying relationship between the first service man-machine conversation engine and the second service man-machine conversation engine, the first state switching instruction can be directly sent to the first service man-machine conversation engine through the general man-machine conversation engine. If a data receiving relation exists between the first service man-machine conversation engine and the second service man-machine conversation engine, the universal man-machine conversation engine can send a first state switching instruction to the first service man-machine conversation engine after the data migration operation is completed.

As can be seen, in this example, when the first business human-machine conversation engine switches from the active state to the standby state according to the first state switching instruction, the first process data generated by the first human-machine conversation engine during the first business human-machine conversation will not be directly cleared. The method and the device are favorable for preventing the situation that the response accuracy and the response efficiency of human-computer interaction are influenced due to data loss under the condition that the user needs to switch to the first business human-computer dialogue engine again to process the third user input statement after the user processes the second user input statement by using the second business human-computer dialogue engine.

In one possible example, after sending the first state switching instruction to the first business human machine dialog engine, the method further includes: detecting whether a preset condition is finished, wherein the preset condition is that a second man-machine conversation carried out by the second service man-machine conversation engine is finished, or the first service man-machine conversation engine continues for a preset time after being switched to a standby state according to the first state switching instruction, or the man-machine conversation frequency of the first service man-machine conversation engine after being switched to the standby state according to the first state switching instruction in the continuous conversation process reaches a preset frequency; if the first service man-machine conversation engine is finished, sending a second state switching instruction to the first service man-machine conversation engine, wherein the second state switching instruction is used for indicating the first service man-machine conversation engine to be switched from a standby state to an inactivated state; if not, the first business man-machine conversation engine continuously keeps a standby state.

When the preset condition is that the second human-computer conversation performed by the second service human-computer conversation engine is ended, the operation that the server sends the processing result aiming at the second user input statement to the terminal device can be used as an end identifier, and if the operation behavior is detected, the preset condition is finished.

When the preset condition is that the first service man-machine conversation engine continues for a preset time after being switched to the standby state according to the first state switching instruction, the preset time can be set according to actual requirements, and further limitation is not performed again.

The number of times of the man-machine conversation after the first business man-machine conversation engine is switched to the standby state according to the first state switching instruction is the number of times input by the user or the number of times that the server responds according to the input sentences of the user in the same continuous conversation process after the first business man-machine conversation engine is switched to the standby state.

In specific implementation, the preset condition may be any one of that the second man-machine conversation performed by the second service man-machine conversation engine is ended, that the first service man-machine conversation engine is switched to the standby state according to the first state switching instruction and then lasts for a preset time, or that the number of man-machine conversations reaches a preset number after the first service man-machine conversation engine is switched to the standby state according to the first state switching instruction in the continuous conversation process. Or, the preset condition may be that no new user voice information from the terminal device is received within a preset time after the end of the continuous session. Of course, the preset conditions may also be any combination of the above contents according to actual requirements, and no further limitation is made herein. The preset conditions are set, so that the possibility that the response accuracy and the response efficiency of the man-machine interaction are influenced by the first business man-machine conversation engine due to data loss can be reduced.

In a specific implementation, if the preset condition is detected to be completed after the first service man-machine conversation engine is switched to the standby state, it can be determined that the first service man-machine conversation engine cannot be switched back in the subsequent conversation. The universal human-machine interaction engine can send a second state switching instruction to the first service human-machine interaction engine at the moment so that the first service human-machine interaction engine is switched from the standby state to the to-be-activated state. When the first business man-machine conversation engine is switched from the standby state to the to-be-activated state, the first business man-machine conversation engine can clear the first process data stored in the first business man-machine conversation engine.

As can be seen, in this example, the first service man-machine conversation engine switches from the standby state to the to-be-activated state after the preset condition is completed, and clears the stored data, so as to reduce the data storage pressure of the server.

In a possible example, after the receiving, by the universal human-machine conversation engine, the first process data, processing the first process data according to a preset data receiving and converting rule to obtain target data, and sending the target data to the second business human-machine conversation engine, the method further includes: and clearing the first process data and the target data stored by the general man-machine conversation engine.

In a specific implementation, the universal human-machine conversation engine may clear the received first process data from the first business human-machine conversation engine after the data migration operation is completed. Or, the universal man-machine conversation engine may clear the first process data after the second business man-machine conversation engine processes the first user input statement and obtains a processing result, so as to improve the data migration efficiency when the user suddenly switches to another business man-machine conversation engine having a data receiving relationship with the first business man-machine conversation engine (for example, when the server processes the first user input statement of "train ticket going to C city after helping me order" but does not obtain feedback information yet, receives the voice information from the terminal device "calculates" or helps me to go to the ticket bar in C city after deciding ").

It can be seen that, in this example, by clearing the first process data from the first business human machine conversation engine and the target data stored by the general human machine conversation engine, the data storage pressure of the server can be further reduced, and more storage space is released.

In a possible example, after the to-be-called business man-machine conversation engine is updated to be the second business man-machine conversation engine, the second business man-machine conversation engine may first obtain the second user input sentence, and then analyze and identify the second user input sentence, so as to determine whether the second business man-machine conversation engine can directly process the second user input sentence to obtain a processing result, that is, whether the data obtained by analyzing the second user input sentence by the second business man-machine conversation engine includes all feature data for processing the second user input sentence. If the second service man-machine conversation engine can directly process the input statement of the second user to obtain a processing result, data migration operation is not needed, and therefore man-machine interaction efficiency can be improved. Illustratively, if the second user input statement is "help me decide to open a high-speed railway ticket to C city tomorrow in the morning", the second business man-machine conversation engine may directly obtain a processing result according to the second user input statement in combination with the current positioning processing.

And if the second business man-machine conversation engine cannot directly process the input statement of the second user to obtain a processing result, performing data migration operation so that the second business man-machine conversation engine acquires target data corresponding to the first key information in the first man-machine conversation according to the data migration operation. And then the second service man-machine conversation engine processes the second user input statement according to the second user input statement and the target data to obtain a processing result, and sends the processing result to the terminal equipment.

If the second business man-machine dialog engine still cannot process the second user input sentence (or the second user input sentence and the target data) to obtain a corresponding processing result, the second business man-machine dialog engine can further process the second user input sentence by combining big data, user portrait and the like. Illustratively, if the first user input statement is "help me define a taxi to mall a tomorrow am", the second user input statement is "help me locate nearby restaurants at a certain time tomorrow afternoon". The second business man-machine dialogue engine may obtain a processing result for the second user input sentence by combining processing of big data (such as scores of restaurants around the destination), user figures (such as user taste habits) and the like on the basis of the second user input sentence (or the second user input sentence and the target data) when processing the second user input sentence, wherein the processing result includes information such as the name and the place of the recommended restaurant, so that reliability of data response can be improved, and business services can be better provided for the user.

The present application may perform the division of the functional units for the server according to the above method example, for example, each functional unit may be divided corresponding to each function, or two or more functions may be integrated into one processing unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit. It should be noted that the division of the unit in the embodiment of the present application is schematic, and is only a logic function division, and there may be another division manner in actual implementation.

Fig. 4 is a block diagram illustrating functional units of a data processing apparatus in a human-computer interaction system according to an embodiment of the present disclosure. The data processing device 30 in the human-computer interaction system can be applied to the server 100 in the human-computer interaction system 10 shown in fig. 1, and the data processing device 30 in the human-computer interaction system includes:

an obtaining unit 310, configured to obtain a first user input sentence from the terminal device;

the obtaining unit is further configured to obtain a second user input sentence from the terminal device in the same continuous session;

a processing unit 320 for determining, by the generic human machine dialog engine, a first semantic recognition result of the first user input sentence, and determining a first business human machine dialog engine adapting the first semantic recognition result;

the processing unit is further configured to call the first user input statement through the first service man-machine dialog engine, process the first user input statement to obtain a first processing result, and send the first processing result to the terminal device;

the processing unit is further configured to receive the data migration instruction through the first service human-computer dialog engine, and complete a data migration operation for the first process data in response to the data migration instruction;

In a possible example, in terms of receiving, by the first business human-machine dialog engine, the data migration instruction and completing, in response to the data migration instruction, a data migration operation with respect to the first process data, the processing unit is specifically configured to: sending the first process data to the general human-machine dialogue engine through the first business human-machine dialogue engine; and receiving the first process data through the general man-machine conversation engine, processing the first process data according to a preset data receiving conversion rule to obtain target data, and sending the target data to the second business man-machine conversation engine.

In a possible example, in the aspect of sending the first process data to the universal human machine dialog engine through the first business human machine dialog engine, the processing unit is specifically configured to: storing first key information in first process data through the first business man-machine conversation engine according to a first form, wherein the first form is a form corresponding to the first business man-machine conversation engine and comprises a plurality of form items, and the first key information is data corresponding to the form items of the first form in the first process data; and sending the first key information to the general man-machine conversation engine through the first business man-machine conversation engine.

In a possible example, in terms of the processing the first process data according to the preset data adapting conversion rule to obtain the target data, the processing unit is specifically configured to: acquiring a first form of the first service man-machine conversation engine and a second form of the second service man-machine conversation engine through the general man-machine conversation engine, wherein the second form is a form corresponding to the second service man-machine conversation engine; determining an incidence relation between a form item corresponding to the first key information in the first form and a form item of the second form through the general man-machine conversation engine, and determining a corresponding preset data carrying conversion rule according to the incidence relation, wherein the incidence relation is at least one of a time incidence relation, a place incidence relation and a person incidence relation; and processing the first key information according to the preset data carrying and converting rule through the universal man-machine conversation engine to obtain the target data.

In one possible example, the processing unit is further specifically configured to: and when the data carrying relationship between the first service man-machine conversation engine and the second service man-machine conversation engine is judged, sending a first state switching instruction to the first service man-machine conversation engine, wherein the first state switching instruction is used for indicating that the first service man-machine conversation engine is switched from an activated state to a standby state.

In one possible example, after said sending of the first state switching instruction to the first business human machine dialog engine, the processing unit is further configured to: detecting whether a preset condition is finished, wherein the preset condition is that a second man-machine conversation carried out by the second service man-machine conversation engine is finished, or the first service man-machine conversation engine continues for a preset time after being switched to a standby state according to the first state switching instruction, or the man-machine conversation frequency of the first service man-machine conversation engine after being switched to the standby state according to the first state switching instruction in the continuous conversation process reaches a preset frequency; if the first service man-machine conversation engine is finished, sending a second state switching instruction to the first service man-machine conversation engine, wherein the second state switching instruction is used for indicating the first service man-machine conversation engine to be switched from a standby state to an inactivated state; if not, the first service man-machine conversation engine continuously keeps a standby state.

In one possible example, the processing unit is further to: and after the first process data is received by the universal man-machine conversation engine, the first process data is processed according to a preset data receiving conversion rule to obtain target data, and the target data is sent to the second business man-machine conversation engine, the first process data and the target data stored by the universal man-machine conversation engine are removed.

In the case of using an integrated unit, a block diagram of functional units of the data processing apparatus 40 in the human-computer interaction system provided in the embodiment of the present application is shown in fig. 5. In fig. 5, a data processing apparatus 40 in the human-computer interaction system includes: a processing module 420 and a communication module 410. The processing module 420 is used for controlling and managing actions of the data processing apparatus 40 in the human-computer interaction system, such as steps performed by the acquisition unit 310, the processing unit 320, and/or other processes for performing the techniques described herein. The communication module 410 is used for supporting interaction between the data processing device 40 and other devices in the human-computer interaction system. As shown in fig. 5, the data processing device 40 in the human-computer interaction system may further include a storage module 430, and the storage module 430 is used for storing program codes and data of the data processing device 40 in the human-computer interaction system.

The processing module 420 may be a processor or a controller, and may be, for example, a Central Processing Unit (CPU), a general-purpose processor, a Digital Signal Processor (DSP), an ASIC, an FPGA or other programmable logic device, a transistor logic device, a hardware component, or any combination thereof. Which may implement or perform the various illustrative logical blocks, modules, and circuits described in connection with the disclosure of the embodiments of the application. The processor may also be a combination of computing functions, e.g., comprising one or more microprocessors, DSPs, and microprocessors, and the like. The communication module 410 may be a transceiver, an RF circuit or a communication interface, etc. The storage module 430 may be a memory.

All relevant contents of each scene related to the method embodiment may be referred to the functional description of the corresponding functional module, and are not described herein again. The data processing device in the human-computer interaction system can execute the steps executed by the server in the data processing method in the human-computer interaction system shown in fig. 3.

Embodiments of the present application also provide a computer storage medium, wherein the computer storage medium stores a computer program for electronic data exchange, the computer program enables a computer to execute part or all of the steps of any one of the methods described in the above method embodiments, and the computer includes a server.

It should be noted that, for simplicity of description, the above-mentioned method embodiments are described as a series of acts or combination of acts, but those skilled in the art will recognize that the present application is not limited by the order of acts described, as some steps may occur in other orders or concurrently depending on the application. Further, those skilled in the art should also appreciate that the embodiments described in the specification are preferred embodiments and that the acts and modules referred to are not necessarily required in this application.

In the foregoing embodiments, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.

In the embodiments provided in the present application, it should be understood that the disclosed apparatus may be implemented in other manners. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the above-described units is only one type of logical functional division, and other divisions may be realized in practice, for example, multiple units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed coupling or direct coupling or communication connection between each other may be through some interfaces, indirect coupling or communication connection between devices or units, and may be in an electrical or other form.

The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.

The integrated unit may be stored in a computer readable memory if it is implemented in the form of a software functional unit and sold or used as a stand-alone product. Based on such understanding, the technical solutions of the present application, which are essential or part of the technical solutions contributing to the prior art, or all or part of the technical solutions, may be embodied in the form of a software product, which is stored in a memory and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the above methods of the embodiments of the present application. And the aforementioned memory comprises: a U-disk, a Read-only memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic disk, or an optical disk, and various media capable of storing program codes.

Those skilled in the art will appreciate that all or part of the steps of the methods of the above embodiments may be implemented by a program, which is stored in a computer-readable memory, the memory including: flash memory disks, read-only memories (ROMs), random Access Memories (RAMs), magnetic or optical disks, and the like.

The foregoing detailed description of the embodiments of the present application has been presented to illustrate the principles and implementations of the present application, and the above description of the embodiments is only provided to help understand the method and the core concept of the present application; meanwhile, for a person skilled in the art, according to the idea of the present application, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present application.

Claims

1. A data processing method in a man-machine interaction system is characterized in that the method is applied to a server in the man-machine interaction system, the man-machine interaction system comprises the server and terminal equipment used by a user for man-machine conversation, the server is provided with a general man-machine conversation engine and a plurality of service man-machine conversation engines used for supporting various different service functions, and the service functions supported by any two man-machine conversation engines are different from each other; the method comprises the following steps:

acquiring a first user input sentence from the terminal equipment;

determining a second semantic recognition result of the second user input sentence through the general man-machine conversation engine, and judging whether the first business man-machine conversation engine can process the second user input sentence;

receiving the first process data through the second business man-machine conversation engine, processing the second user input statement according to the first process data to obtain a third processing result, and sending the third processing result to the terminal equipment;

and if not, receiving a second user input statement from the general man-machine conversation engine through the second service man-machine conversation engine, and processing the second user input statement to obtain a fourth processing result.

2. The method of claim 1, wherein receiving, by the first business human-machine dialog engine, the data migration instruction and completing, in response to the data migration instruction, the data migration operation for the first process data comprises:

sending the first process data to the general human-machine dialogue engine through the first business human-machine dialogue engine;

and receiving the first process data through the general man-machine conversation engine, processing the first process data according to a preset data receiving conversion rule to obtain target data, and sending the target data to the second business man-machine conversation engine.

3. The method of claim 2, wherein said sending, by said first business human machine dialog engine, said first process data to said general human machine dialog engine comprises:

storing first key information in first process data through the first business man-machine conversation engine according to a first form, wherein the first form is a form corresponding to the first business man-machine conversation engine and comprises a plurality of form items, and the first key information is data corresponding to the form items of the first form in the first process data;

and sending the first key information to the general man-machine conversation engine through the first business man-machine conversation engine.

4. The method of claim 3, wherein processing the first process data according to a predetermined data reception transformation rule to obtain target data comprises:

acquiring a first form of the first service man-machine conversation engine and a second form of the second service man-machine conversation engine through the general man-machine conversation engine, wherein the second form is a form corresponding to the second service man-machine conversation engine;

determining an incidence relation between a form item corresponding to the first key information in the first form and a form item of the second form through the general man-machine conversation engine, and determining a corresponding preset data carrying conversion rule according to the incidence relation, wherein the incidence relation is at least one of a time incidence relation, a place incidence relation and a person incidence relation;

and processing the first key information according to the preset data carrying conversion rule through the universal man-machine conversation engine to obtain the target data.

5. The method of claim 1, wherein after determining whether a data receiving relationship exists between the first business human machine dialog engine and the second business human machine dialog engine, the method further comprises:

and if the first state switching instruction exists, sending a first state switching instruction to the first service man-machine conversation engine, wherein the first state switching instruction is used for indicating the first service man-machine conversation engine to be switched from an activated state to a standby state.

6. The method of claim 5, wherein after sending the first stateful switchover instruction to the first business human machine dialog engine, the method further comprises:

detecting whether a preset condition is finished, wherein the preset condition is that a second man-machine conversation carried out by the second service man-machine conversation engine is finished, or the first service man-machine conversation engine continues for a preset time after being switched to a standby state according to the first state switching instruction, or the man-machine conversation frequency of the first service man-machine conversation engine after being switched to the standby state according to the first state switching instruction in the continuous conversation process reaches a preset frequency;

if the first service man-machine conversation engine is finished, sending a second state switching instruction to the first service man-machine conversation engine, wherein the second state switching instruction is used for indicating the first service man-machine conversation engine to be switched from a standby state to an inactivated state;

if not, the first business man-machine conversation engine continuously keeps a standby state.

7. The method of claim 2, wherein after receiving the first process data by the universal human machine dialog engine, processing the first process data according to a preset data reception and conversion rule to obtain target data, and sending the target data to the second business human machine dialog engine, the method further comprises:

and clearing the first process data and the target data stored by the general man-machine conversation engine.

8. A data processing device in a man-machine interaction system is characterized in that the data processing device is applied to a server in the man-machine interaction system, the man-machine interaction system comprises the server and terminal equipment used by a user for man-machine interaction, the server is provided with a general man-machine interaction engine and a plurality of service man-machine interaction engines used for supporting various different service functions, and the service functions supported by any two man-machine interaction engines are different from each other; the device comprises:

a processing unit for determining a first semantic recognition result of the first user input sentence and determining a first business human-machine dialog engine adapting the first semantic recognition result by the general human-machine dialog engine;

if the processing is impossible, determining a second service man-machine conversation engine adapted to the second semantic recognition result through the general man-machine conversation engine, and judging whether a data carrying relationship exists between the first service man-machine conversation engine and the second service man-machine conversation engine, wherein the data carrying relationship means that first process data generated by the first service man-machine conversation engine in a first man-machine conversation process comprises characteristic data required by the second service man-machine conversation engine in a second man-machine conversation process;

9. A server, comprising a processor, memory, a communication interface, and one or more programs stored in the memory and configured to be executed by the processor, the programs including instructions for performing the steps in the method of any of claims 1-7.

10. A computer-readable storage medium, characterized in that a computer program for electronic data exchange is stored, wherein the computer program causes a computer to perform the steps in the method according to any of claims 1-7.