CN110738982B - Request processing method and device and electronic equipment - Google Patents
Request processing method and device and electronic equipment Download PDFInfo
- Publication number
- CN110738982B CN110738982B CN201911008200.0A CN201911008200A CN110738982B CN 110738982 B CN110738982 B CN 110738982B CN 201911008200 A CN201911008200 A CN 201911008200A CN 110738982 B CN110738982 B CN 110738982B
- Authority
- CN
- China
- Prior art keywords
- request
- interface
- preset
- user request
- text
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000003672 processing method Methods 0.000 title claims description 27
- 238000012545 processing Methods 0.000 claims abstract description 149
- 238000000034 method Methods 0.000 claims abstract description 52
- 238000006243 chemical reaction Methods 0.000 claims abstract description 30
- 230000008569 process Effects 0.000 claims abstract description 28
- 230000002159 abnormal effect Effects 0.000 claims abstract description 25
- 238000004590 computer program Methods 0.000 claims description 9
- 238000004891 communication Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 4
- 238000007726 management method Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L13/00—Speech synthesis; Text to speech systems
- G10L13/02—Methods for producing synthetic speech; Speech synthesisers
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L13/00—Speech synthesis; Text to speech systems
- G10L13/02—Methods for producing synthetic speech; Speech synthesisers
- G10L13/04—Details of speech synthesis systems, e.g. synthesiser structure or memory management
Landscapes
- Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Telephonic Communication Services (AREA)
Abstract
The method comprises the steps of calling a first interface to process an obtained user request to obtain a second interface corresponding to the user request, sending the user request to the corresponding second interface to perform text-to-speech conversion processing on a request text included in the user request to obtain a processing result of the user request, and acquiring a speech text corresponding to the user request from a preset knowledge graph when the processing result is abnormal. By the method, the voice text corresponding to the user request is searched from the knowledge graph when the interface corresponding to the user request has an error, so that the efficiency of obtaining the voice text corresponding to the user request is improved, the disaster tolerance performance of the system is improved, and the problem that the request processing speed is too slow due to the fact that the second interface needs to be called repeatedly for many times under the condition that the second interface corresponding to the user request has an error in the prior art is solved.
Description
Technical Field
The present application relates to the field of data processing technologies, and in particular, to a request processing method and apparatus, and an electronic device.
Background
With the progress of computer technology and the development of society, people have more and more demands on digital service in the internet, and users can conveniently process the digital service in a digital service system through terminals, so the digital service is popular with the majority of users.
In current digital service systems, when a request initiated by a user is received, an interface (request processing unit) for processing the request is generally selected to process the service request. However, when a problem occurs in an interface (request processing unit) that processes a certain request, the corresponding request interface (request processing unit) is required to be repeatedly requested for processing the request, which may seriously reduce the efficiency of request processing and the disaster tolerance performance of the digital service system.
Disclosure of Invention
In view of the above problems, the present application provides a request processing method, a request processing device, and an electronic device, so as to effectively alleviate the problems in the prior art that when an interface for processing a request is faulty, the efficiency of request processing is low and the disaster tolerance performance of a digital service system is poor.
In a first aspect, the present application provides a request processing method, including:
acquiring a user request;
calling a first interface to process the user request to obtain a second interface corresponding to the user request;
sending the user request to a corresponding second interface to perform text-to-speech conversion processing on a request text included in the user request so as to obtain a processing result of the user request;
and when the processing result is abnormal, acquiring a voice text corresponding to the user request from a preset knowledge graph.
According to an embodiment of the present application, optionally, in the request processing method, invoking a first interface to process the user request to obtain a second interface corresponding to the user request includes:
calling a first interface to analyze the user request so as to obtain address information, interface request parameters and a request text included in the user request;
searching a second interface corresponding to the address information from a plurality of second interfaces;
sending the user request to a corresponding second interface for text-to-speech conversion processing to obtain a processing result corresponding to the user request, including:
and sending the user request to a corresponding second interface so that the second interface performs text-to-speech conversion processing on the request text according to the interface request parameters to obtain a processing result.
According to an embodiment of the application, optionally, in the request processing method, the preset knowledge graph includes interface addresses of the plurality of second interfaces, an interface parameter corresponding to each interface address, a preset request corresponding to each interface parameter, and a speech text corresponding to each preset request.
According to an embodiment of the present application, optionally, in the request processing method, acquiring a speech text corresponding to the user request from a preset knowledge graph includes:
searching a target interface address corresponding to the address information included in the user request from the interface addresses of the plurality of second interfaces;
and searching the target interface parameter corresponding to the interface request parameter from the interface parameter corresponding to the target interface address, and acquiring the voice text corresponding to the target interface parameter.
According to an embodiment of the present application, optionally, in the request processing method, the voice text corresponding to the preset request is obtained by:
calling a first interface to process a preset request to obtain a second interface corresponding to the preset request;
sending the preset request to a corresponding second interface to perform text-to-speech conversion processing, so as to obtain a processing result corresponding to the preset request, wherein the processing result is normal or abnormal;
and when the processing result corresponding to the preset request is normal, acquiring the voice text included in the processing result.
According to an embodiment of the present application, optionally, in the request processing method, the method further includes:
and when the processing result corresponding to the preset request is abnormal, returning to the step of executing the step of sending the preset request to the corresponding second interface for text-to-speech conversion processing to obtain the processing result corresponding to the preset request, and obtaining the speech text included in the processing result until the processing result is normal.
According to an embodiment of the present application, optionally, in the request processing method, the method further includes:
when the processing result corresponding to the preset request is abnormal, adding a second interface corresponding to the preset request into a request error pool;
sending the preset request to a corresponding second interface in an error pool at intervals of preset duration to perform text-to-speech conversion processing, so as to obtain a processing result corresponding to the preset request;
and when the processing result corresponding to the preset request is normal, removing the second interface corresponding to the preset request from the error pool, and taking the voice text included in the processing result and the preset request corresponding to the processing result as preset data.
In a second aspect, the present application provides a request processing apparatus, including:
the request acquisition module is used for acquiring a user request;
the first processing module is used for calling a first interface to process the user request so as to obtain a second interface corresponding to the user request;
the second processing module is used for sending the user request to a corresponding second interface to perform text-to-speech conversion processing so as to obtain a processing result corresponding to the user request;
and the voice text acquisition module is used for acquiring the voice text corresponding to the user request from the preset knowledge graph when the processing result is abnormal.
In a second aspect, the present application provides a storage medium storing a computer program executable by one or more processors and operable to implement a request processing method as described above.
In a third aspect, the present application provides an electronic device, comprising a memory and a processor, wherein the memory stores a computer program, and the computer program is executed by the processor to perform the request processing method.
Compared with the prior art, one or more embodiments in the above scheme can have the following advantages or beneficial effects:
the method comprises the steps of calling a first interface to process an obtained user request to obtain a second interface corresponding to the user request, sending the user request to the corresponding second interface to carry out text-to-speech conversion processing on a request text included in the user request to obtain a processing result of the user request, and obtaining a speech text corresponding to the user request from a preset knowledge graph when the processing result is abnormal. The method and the device realize that the voice text corresponding to the user request is searched from the knowledge graph when the interface corresponding to the user request has an error, so that the efficiency of obtaining the voice text corresponding to the user request is improved, the disaster tolerance performance of the system is further improved, and the problem that the request processing speed is too slow due to the fact that the second interface needs to be called repeatedly for many times under the condition that the second interface corresponding to the user request has an error in the prior art is solved.
Drawings
The present application will be described in more detail below on the basis of embodiments and with reference to the accompanying drawings.
Fig. 1 is a flowchart illustrating a request processing method according to an embodiment of the present application.
Fig. 2 is a schematic flowchart of step S110 in fig. 1.
Fig. 3 is a schematic diagram of a preset knowledge graph according to an embodiment of the present application.
Fig. 4 is another flowchart illustrating a request processing method according to an embodiment of the present application.
In the drawings, like parts are designated with like reference numerals, and the drawings are not drawn to scale.
Detailed Description
The following detailed description will be provided with reference to the accompanying drawings and embodiments, so that how to apply the technical means to solve the technical problems and achieve the corresponding technical effects can be fully understood and implemented. The embodiments and various features in the embodiments of the present application can be combined with each other without conflict, and the formed technical solutions are all within the scope of protection of the present application.
Example one
In the embodiment of the present invention, a user may send a user request to a server through a user terminal, where the user request includes a request text, and the request text needs to be subjected to text-to-speech conversion to obtain a speech text.
When the server receives the request Text, the request Text is transmitted To a TTS dispatching center (TTS: Text To Speech from Text To Speech) so as To carry out Text-To-Speech conversion processing in the TTS dispatching center To obtain a processing result, wherein, when the processing result is normal, the processing result comprises a voice text corresponding to the user request, and when the processing result is abnormal, the speech text included in the processing result does not correspond to the user request, or the speech text is not included in the processing result, when the request result obtained by the server processing the user request is abnormal, the voice text corresponding to the user request is obtained from the knowledge graph, thereby improving the efficiency of obtaining the voice text corresponding to the user request, and the disaster tolerance performance of the system is further improved, and the problem that the request processing speed is too slow due to the fact that the second interface needs to be called repeatedly for many times under the condition that the second interface corresponding to the user request is wrong in the prior art is solved.
Fig. 1 is an interaction flowchart illustrating a response method for a service request according to a first embodiment of the present invention, where the method is applicable to an electronic device such as a server or a user terminal, and the steps S110 to S140 are executed when the application management method is applied to the electronic device.
Step S110: and constructing a preset knowledge graph comprising a plurality of preset requests and the corresponding voice texts corresponding to each preset request.
It is to be understood that, in the step S110, a specific manner of constructing the preset knowledge graph may include obtaining a speech text corresponding to a preset request, and constructing the preset knowledge graph according to the preset request and the speech text corresponding to the preset request. The method for obtaining the voice text corresponding to the preset request may be based on user input, or may be obtained by processing the preset request.
Referring to fig. 2, optionally, in this embodiment, the speech text corresponding to each preset request may be obtained in the following manner:
step S112: and calling a first interface to process a preset request so as to obtain a second interface corresponding to the preset request.
The first interface and the second interface may be function interfaces, and the functions corresponding to the first interface and the second interface are different, so that when the preset request calls the first interface and the second interface, the first interface and the second interface can perform different processing or operation on the user request. In this embodiment, the first interface is configured to analyze the preset request to obtain address information of the second interface and interface request parameters included in the preset request, and search, according to the address information of the second interface included in the analyzed preset request, a second interface corresponding to the preset request from the plurality of second interfaces, where the second interface is configured to perform text-to-speech conversion operation on a request text in the preset request according to parameters obtained by interface conditions to obtain a speech text.
In this embodiment, the number of the second interfaces is multiple, and the address information of different second interfaces is different, and each second interface may have multiple interface parameters, so that the same second interface may process different preset requests.
Step S114: and sending the preset request to a corresponding second interface to perform text-to-speech conversion processing, so as to obtain a processing result corresponding to the preset request.
Wherein the processing result is normal or abnormal. It should be noted that, when the processing result is normal, the processing result includes a speech text corresponding to the preset request, and when the processing result is abnormal, the speech text included in the processing result is not the speech text corresponding to the preset request or the processing result does not include the speech text.
Step S116: and when the processing result corresponding to the preset request is normal, acquiring the voice text included in the processing result.
In this embodiment, when the request result corresponding to the preset request is abnormal, the method further includes returning to the step 114 until the obtained processing result is normal, and acquiring the voice text included in the processing result.
It can be understood that, in this embodiment, when the processing result corresponding to the preset request is abnormal, the method may further include: adding the second interface corresponding to the preset request into a request error pool, sending the preset request to a corresponding second interface in the error pool at intervals of preset duration to perform text-to-speech conversion processing, obtaining a processing result corresponding to the preset request, removing the second interface corresponding to the preset request from the error pool when the processing result corresponding to the preset request is normal, and taking the speech text included in the processing result and the preset request corresponding to the processing result as preset data.
When the processing result corresponding to the preset request is abnormal, the second interface corresponding to the preset request is added into the request error pool, and when the processing result is normal, the corresponding second interface is removed, so that the second interface is reused, the memory increase caused by newly adding the function of the second interface is avoided, and the human resources are effectively saved. The preset time period may be, but is not limited to, 1 second, 2 seconds, or 5 seconds, and is not specifically limited herein, and may be set according to actual requirements.
It can be understood that, in this embodiment, the preset knowledge graph may further include address information of a second interface that processes the preset request, and interface request parameters and the like corresponding to the second interface. The specific illustration of the preset knowledge graph may be as shown in fig. 3 (fig. 3 only shows address information including one second interface), and the preset knowledge graph may be constructed according to an interface address of each second interface, an interface parameter corresponding to each interface address, a preset request corresponding to each interface parameter, and an association relationship between each two voice texts corresponding to each preset request.
Step S120: a user request is obtained.
In step S120, a user request sent by a user terminal, such as a mobile phone, a computer, or a tablet computer, may be received, where the user request may include a request text, address information (IP address) of a second interface that can be called to process the request text, and interface request parameters of the interface, and it should be noted that the request text is a character string that is expected to perform TTS operation.
Step S130: and calling a first interface to process the user request so as to obtain a second interface corresponding to the user request.
The first interface and the second interface are function interfaces, the first interface is used for analyzing a user request to obtain address information of the second interface and interface request parameters included in a preset request, the second interface corresponding to the preset request is searched from the plurality of second interfaces according to the address information of the second interface included in the analyzed user request, and the second interface is used for performing text-to-speech conversion operation on a request text in the preset request according to interface condition parameters to obtain a speech text.
In step S130, specifically, the first interface is called to analyze the user request to obtain address information, interface request parameters, and a request text included in the user request, and a second interface corresponding to the address information is searched from a plurality of second interfaces.
Step S140: and sending the user request to a corresponding second interface to perform text-to-speech conversion processing on a request text included in the user request so as to obtain a processing result of the user request.
In step S140, the request text and the interface request parameter may be respectively sent to corresponding second interfaces according to address information of the second interfaces in the user request, so that the second interfaces perform text-to-speech conversion processing on the request text according to the interface request parameter to obtain processing interfaces, where when a processing result of the user request is normal, the processing result includes a speech text corresponding to the user request, and when the processing result of the user request is abnormal, the processing result does not include the speech text, or the included speech text does not correspond to the user request.
Step S150: and when the processing result is abnormal, acquiring a voice text corresponding to the user request from the preset knowledge graph.
In step S150, according to the knowledge graph shown in fig. 3, a target interface address corresponding to the address information included in the user request is searched from the interface addresses of the plurality of second interfaces, a target interface parameter corresponding to the interface request parameter is searched from the interface parameters corresponding to the target interface address, and a speech text corresponding to the target interface parameter is obtained.
By adopting the above arrangement, in the request processing method adopted in the present application, by constructing the preset knowledge graph including the plurality of preset requests and the corresponding voice texts corresponding to each preset request, when the user request is obtained, the first interface is invoked to process the user request so as to obtain the second interface corresponding to the user request, the user request is sent to the corresponding second interface so as to perform text-to-voice conversion processing on the request texts included in the user request so as to obtain the processing result of the user request, and when the processing result is abnormal, the voice texts corresponding to the user request are obtained from the preset knowledge graph. On one hand, when an interface corresponding to a user request is wrong, the speech text corresponding to the user request is searched from the knowledge graph, so that the efficiency of obtaining the speech text corresponding to the user request is improved, the disaster tolerance performance of the system is further improved, and the problem that the request processing speed is too slow due to the fact that the second interface needs to be called repeatedly for many times under the condition that the second interface corresponding to the user request is wrong in the prior art is solved. On the other hand, by constructing the preset knowledge graph comprising the plurality of preset requests and the voice text corresponding to each preset request, the query efficiency of querying the corresponding voice text can be improved when the second interface corresponding to the user request has an error, so that the efficiency of acquiring the voice text corresponding to the user request is further improved, and the disaster tolerance performance of the system is improved.
Referring to fig. 4, the embodiment further provides a specific request processing method, which specifically executes the following processes: the method comprises the steps of obtaining a user request and transmitting the user request to a TTS (text to transfer) scheduling center, calling a first interface to analyze the user request to obtain address information, interface request parameters and a request text of a second interface included in the user request, determining an interface corresponding to the user request from a plurality of interfaces according to the address information of the second interface, sending the user request to the corresponding second interface to request to call the second interface to perform text-to-speech conversion processing to obtain a processing result, and if the processing result includes a speech text corresponding to the request text, obtaining the speech text corresponding to the request text; if no voice text corresponding to the request text exists in the processing result or the voice result included in the processing result is wrong, adding the second interface into a wrong pool, calling the second interface corresponding to the user request in the wrong pool at intervals of preset duration to process the user request, removing the second interface from the wrong pool when the processing result obtained by processing the user request is normal, and adding the address information of the second interface, the interface request parameter of the second interface when processing the user request, the request text and the voice text included in the processing result and corresponding to the request text into a knowledge graph to obtain a preset knowledge graph.
When the user request is obtained again and transmitted to the TTS dispatching center, the first interface is called again to process the user request to obtain address information, interface request parameters and a request text of a second interface included in the user request, so that a result corresponding to the user request is determined from the multiple interfaces according to the address information of the second interface, and when the processing result is abnormal, a voice text corresponding to the user request is searched from a preset knowledge graph according to the address information, the interface request parameters and the request text of the second interface included in the user request.
Example two
An embodiment of the present application further provides a request processing apparatus, where the apparatus includes:
the map building module is used for building a preset knowledge map which comprises a plurality of preset requests and the corresponding voice texts corresponding to the preset requests.
Since the map building block is similar to the implementation principle of step S110 in fig. 1, it will not be further described here.
And the request acquisition module is used for acquiring the user request.
Since the implementation principle of the request obtaining module is similar to that of step S120 in fig. 1, no further description is made here.
And the first processing module is used for calling a first interface to process the user request so as to obtain a second interface corresponding to the user request.
Since the first processing module is similar to step S130 in fig. 1, the implementation principle of step S130 is not further described here.
And the second processing module is used for sending the user request to a corresponding second interface for text-to-speech conversion processing so as to obtain a processing result corresponding to the user request.
Since the second processing module is similar to the implementation principle of step S140 in fig. 1, it will not be further described here.
And the voice text acquisition module is used for acquiring the voice text corresponding to the user request from the preset knowledge graph when the processing result is abnormal.
Since the speech text acquisition module is similar to the implementation principle of step S150 in fig. 1, it will not be further described here.
EXAMPLE III
The present embodiment further provides a storage medium, such as a flash memory, a hard disk, a multimedia card, a card-type memory (e.g., an SD or DX memory, etc.), a Random Access Memory (RAM), a Static Random Access Memory (SRAM), a Read Only Memory (ROM), an Electrically Erasable Programmable Read Only Memory (EEPROM), a Programmable Read Only Memory (PROM), a magnetic memory, a magnetic disk, an optical disk, a server, an App application mall, etc., where a computer program is stored, and when the computer program is executed by a processor, the request processing method in the first embodiment can be implemented, and specific embodiment procedures of steps of the request processing method may be referred to in the first embodiment, and details of the steps are not repeated here.
Example four
The embodiment of the present application provides an electronic device, which may be a server, or a mobile phone, a computer, or a tablet computer, and the electronic device includes a memory and a processor, where the memory stores a computer program, and the computer program, when executed by the processor, implements the application management method as described in the first embodiment. It is to be appreciated that the electronic device can also include input/output (I/O) interfaces, as well as communication components.
Wherein, the processor is used for executing all or part of the steps in the application management method in the first embodiment. The memory is used to store various types of data, which may include, for example, instructions for any application or method in the electronic device, as well as application-related data.
The Processor may be an Application Specific Integrated Circuit (ASIC), a Digital Signal Processor (DSP), a Digital Signal Processing Device (DSPD), a Programmable Logic Device (PLD), a Field Programmable Gate Array (FPGA), a controller, a microcontroller, a microprocessor, or other electronic components, and is configured to perform the request Processing method in the first embodiment.
The Memory may be implemented by any type of volatile or non-volatile Memory device or combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read-Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (ROM), magnetic Memory, flash Memory, magnetic disk or optical disk.
The I/O interface provides an interface between the processor and other interface modules, such as a keyboard, mouse, buttons, etc. These buttons may be virtual buttons or physical buttons.
The communication component is used for carrying out wired or wireless communication between the electronic equipment and other equipment. Wireless Communication, such as Wi-Fi, bluetooth, Near Field Communication (NFC), 2G, 3G, or 4G, or a combination of one or more of them, so that the corresponding Communication component 405 may include: Wi-Fi module, bluetooth module, NFC module.
In summary, according to the request processing method, the request processing device and the electronic device provided by the application, the method processes the obtained user request by calling the first interface to obtain the second interface corresponding to the user request, sends the user request to the corresponding second interface to perform text-to-speech conversion processing on the request text included in the user request to obtain the processing result of the user request, and obtains the speech text corresponding to the user request from the preset knowledge graph when the processing result is abnormal. By the method, when the interface corresponding to the user request is wrong, the voice text corresponding to the user request is searched from the knowledge graph, so that the efficiency of obtaining the voice text corresponding to the user request is improved, the disaster tolerance performance of the system is further improved, and the problem that the request processing speed is too slow due to the fact that the second interface needs to be called repeatedly for many times under the condition that the second interface corresponding to the user request is wrong in the prior art is solved. Further, by constructing a preset knowledge graph comprising a plurality of preset requests and the voice text corresponding to each preset request, the query efficiency of querying the corresponding voice text can be improved when the second interface corresponding to the user request has an error, so that the efficiency of obtaining the voice text corresponding to the user request is further improved, and the disaster tolerance performance of the system is improved.
In the several embodiments provided in the embodiments of the present application, it should be understood that the disclosed system and method may be implemented in other ways. The system and method embodiments described above are merely illustrative.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
Although the embodiments disclosed in the present application are described above, the descriptions are only for the convenience of understanding the present application, and are not intended to limit the present application. It will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the disclosure as defined by the appended claims.
Claims (8)
1. A method for processing a request, the method comprising:
acquiring a user request;
calling a first interface to process the user request to obtain a second interface corresponding to the user request, and calling the first interface to process the user request to obtain the second interface corresponding to the user request, wherein the method comprises the following steps: calling a first interface to analyze the user request so as to obtain address information, interface request parameters and a request text included in the user request; searching a second interface corresponding to the address information from a plurality of second interfaces; sending the user request to a corresponding second interface for text-to-speech conversion processing to obtain a processing result corresponding to the user request, including: sending the user request to a corresponding second interface so that the second interface performs text-to-speech conversion processing on the request text according to the interface request parameters to obtain a processing result;
sending the user request to a corresponding second interface to perform text-to-speech conversion processing on a request text included in the user request so as to obtain a processing result of the user request;
and when the processing result is abnormal, acquiring the voice text corresponding to the user request from a preset knowledge graph, wherein the preset knowledge graph comprises interface addresses of a plurality of second interfaces, interface parameters corresponding to each interface address, preset requests corresponding to each interface parameter and voice texts corresponding to each preset request.
2. The request processing method of claim 1, wherein obtaining the speech text corresponding to the user request from a predetermined knowledge-graph comprises:
searching a target interface address corresponding to the address information included in the user request from the interface addresses of the plurality of second interfaces;
and searching the target interface parameter corresponding to the interface request parameter from the interface parameter corresponding to the target interface address, and acquiring the voice text corresponding to the target interface parameter.
3. The request processing method according to claim 1, wherein the speech text corresponding to the preset request is obtained by:
calling a first interface to process a preset request to obtain a second interface corresponding to the preset request;
sending the preset request to a corresponding second interface to perform text-to-speech conversion processing, so as to obtain a processing result corresponding to the preset request, wherein the processing result is normal or abnormal;
and when the processing result corresponding to the preset request is normal, acquiring the voice text included in the processing result.
4. The request processing method of claim 3, further comprising:
and when the processing result corresponding to the preset request is abnormal, returning to the step of executing the step of sending the preset request to the corresponding second interface for text-to-speech conversion processing to obtain the processing result corresponding to the preset request, and obtaining the speech text included in the processing result until the processing result is normal.
5. The request processing method of claim 3, further comprising:
when the processing result corresponding to the preset request is abnormal, adding a second interface corresponding to the preset request into a request error pool;
sending the preset request to a corresponding second interface in an error pool at intervals of preset duration to perform text-to-speech conversion processing, so as to obtain a processing result corresponding to the preset request;
and when the processing result corresponding to the preset request is normal, removing the second interface corresponding to the preset request from the error pool, and taking the voice text included in the processing result and the preset request corresponding to the processing result as preset data.
6. A request processing apparatus, comprising:
the request acquisition module is used for acquiring a user request;
the first processing module is configured to invoke a first interface to process the user request to obtain a second interface corresponding to the user request, and invoke the first interface to process the user request to obtain the second interface corresponding to the user request, and includes: calling a first interface to analyze the user request so as to obtain address information, interface request parameters and a request text included in the user request; searching a second interface corresponding to the address information from a plurality of second interfaces; sending the user request to a corresponding second interface for text-to-speech conversion processing to obtain a processing result corresponding to the user request, including: sending the user request to a corresponding second interface so that the second interface performs text-to-speech conversion processing on the request text according to the interface request parameters to obtain a processing result;
the second processing module is used for sending the user request to a corresponding second interface to perform text-to-speech conversion processing so as to obtain a processing result corresponding to the user request;
and the voice text acquisition module is used for acquiring the voice text corresponding to the user request from a preset knowledge graph when the processing result is abnormal, wherein the preset knowledge graph comprises interface addresses of a plurality of second interfaces, interface parameters corresponding to each interface address, a preset request corresponding to each interface parameter and the voice text corresponding to each preset request.
7. A storage medium storing a computer program executable by one or more processors to perform a request processing method according to any one of claims 1 to 5.
8. An electronic device, comprising a memory and a processor, the memory having stored thereon a computer program that, when executed by the processor, performs a request processing method according to any one of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911008200.0A CN110738982B (en) | 2019-10-22 | 2019-10-22 | Request processing method and device and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911008200.0A CN110738982B (en) | 2019-10-22 | 2019-10-22 | Request processing method and device and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110738982A CN110738982A (en) | 2020-01-31 |
| CN110738982B true CN110738982B (en) | 2022-01-28 |
Family
ID=69270885
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911008200.0A Active CN110738982B (en) | 2019-10-22 | 2019-10-22 | Request processing method and device and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110738982B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102427465A (en) * | 2011-08-18 | 2012-04-25 | 青岛海信电器股份有限公司 | Voice service proxy method and device and system for integrating voice application through proxy |
| CN103501382A (en) * | 2013-09-17 | 2014-01-08 | 小米科技有限责任公司 | Voice service providing method, device and terminal |
| CN106156365A (en) * | 2016-08-03 | 2016-11-23 | 北京智能管家科技有限公司 | A kind of generation method and device of knowledge mapping |
| CN107180059A (en) * | 2016-03-11 | 2017-09-19 | 北大方正集团有限公司 | Data retrieval method and data retrieval system |
| CN107591039A (en) * | 2017-09-28 | 2018-01-16 | 武汉海鲸教育科技有限公司 | A kind of intellectual education learning platform |
| CN109102809A (en) * | 2018-06-22 | 2018-12-28 | 北京光年无限科技有限公司 | A kind of dialogue method and system for intelligent robot |
| WO2019027992A1 (en) * | 2017-08-03 | 2019-02-07 | Telepathy Labs, Inc. | Omnichannel, intelligent, proactive virtual agent |
| CN109995833A (en) * | 2017-12-29 | 2019-07-09 | 顺丰科技有限公司 | Voice service providing method, server, client, system, equipment and medium |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8140335B2 (en) * | 2007-12-11 | 2012-03-20 | Voicebox Technologies, Inc. | System and method for providing a natural language voice user interface in an integrated voice navigation services environment |
| US9378065B2 (en) * | 2013-03-15 | 2016-06-28 | Advanced Elemental Technologies, Inc. | Purposeful computing |
| US10922360B2 (en) * | 2017-08-30 | 2021-02-16 | International Business Machines Corporation | Ancillary speech generation via query answering in knowledge graphs |
| US20190080245A1 (en) * | 2017-09-08 | 2019-03-14 | Niantic, Inc. | Methods and Systems for Generation of a Knowledge Graph of an Object |
| CN109145123B (en) * | 2018-09-30 | 2020-11-17 | 国信优易数据股份有限公司 | Knowledge graph model construction method, intelligent interaction method and system and electronic equipment |
| CN109697233B (en) * | 2018-12-03 | 2023-06-20 | 中电科大数据研究院有限公司 | Knowledge graph system construction method |
| CN110277086B (en) * | 2019-06-25 | 2021-11-19 | 中国科学院自动化研究所 | Voice synthesis method and system based on power grid dispatching knowledge graph and electronic equipment |
-
2019
- 2019-10-22 CN CN201911008200.0A patent/CN110738982B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102427465A (en) * | 2011-08-18 | 2012-04-25 | 青岛海信电器股份有限公司 | Voice service proxy method and device and system for integrating voice application through proxy |
| CN103501382A (en) * | 2013-09-17 | 2014-01-08 | 小米科技有限责任公司 | Voice service providing method, device and terminal |
| CN107180059A (en) * | 2016-03-11 | 2017-09-19 | 北大方正集团有限公司 | Data retrieval method and data retrieval system |
| CN106156365A (en) * | 2016-08-03 | 2016-11-23 | 北京智能管家科技有限公司 | A kind of generation method and device of knowledge mapping |
| WO2019027992A1 (en) * | 2017-08-03 | 2019-02-07 | Telepathy Labs, Inc. | Omnichannel, intelligent, proactive virtual agent |
| CN107591039A (en) * | 2017-09-28 | 2018-01-16 | 武汉海鲸教育科技有限公司 | A kind of intellectual education learning platform |
| CN109995833A (en) * | 2017-12-29 | 2019-07-09 | 顺丰科技有限公司 | Voice service providing method, server, client, system, equipment and medium |
| CN109102809A (en) * | 2018-06-22 | 2018-12-28 | 北京光年无限科技有限公司 | A kind of dialogue method and system for intelligent robot |
Non-Patent Citations (2)
| Title |
|---|
| Knowledge Graph Inference for spoken dialog systems;YiMa，et al.;《2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)》;IEEE;20150806;全文 * |
| 基于知识图谱的智能决策支持技术及应用研究;魏瑾等;《计算机技术与发展》;中国知网;20190925;第30卷(第1期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110738982A (en) | 2020-01-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR102245025B1 (en) | Memory return method and device | |
| KR102194052B1 (en) | Service execution method and device | |
| CN107360261B (en) | HTTP request processing method and device and electronic equipment | |
| JP2019503537A (en) | Method and apparatus for processing short link and short link server | |
| CN108846100A (en) | The method and apparatus of fast search boarding application | |
| CN113366815A (en) | Network resource request method, device, electronic equipment and storage medium | |
| CN110851987B (en) | Method, apparatus and storage medium for predicting calculated duration based on acceleration ratio | |
| CN110943934A (en) | Service request processing method, system, terminal and readable storage medium | |
| CN105827798B (en) | Position information processing method and electronic equipment | |
| CN113536174A (en) | Interface loading method, device and equipment | |
| CN104618388A (en) | Quick registration and login method and corresponding reset server and information server | |
| CN115329170A (en) | Webpage crawling method, device, equipment and storage medium | |
| KR102205686B1 (en) | Method and apparatus for ranking candiate character and method and device for inputting character | |
| CN111770043A (en) | Game data communication method, device, storage medium and electronic equipment | |
| CN111488286B (en) | Method and device for independently developing Android modules | |
| CN111078437B (en) | Remote calling method and device for verification codes, electronic equipment and readable storage medium | |
| CN110738982B (en) | Request processing method and device and electronic equipment | |
| CN110673970B (en) | Cross-process calling system and method based on web application | |
| WO2015003570A1 (en) | Data downloading method,device and system thereof | |
| CN108600255B (en) | Mock service management method, device, computer equipment and storage medium | |
| CN111124627A (en) | Method, device, terminal and storage medium for determining application program caller | |
| US9736176B2 (en) | System and method for detecting security exposures of VOIP devices | |
| CN113421565A (en) | Search method, search device, electronic equipment and storage medium | |
| CN114253441A (en) | Target function starting method and device, storage medium and electronic device | |
| CN109150951B (en) | Method and device for starting Activity of Android system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |