Method and apparatus for processing in-vehicle semantic results

Abstract

The application provides a vehicle-mounted semantic result processing method and device. The method comprises the following steps: obtaining to-be-recognized text data corresponding to a vehicle-mounted voice signal; determining the type of the to-be-recognized text data according to the to-be-recognized text data; when the type of the to-be-recognized text data is a vehicle type, processing the to-be-recognized text data through a local natural language understanding service to obtain a local semantic result; when the local semantic result is a preset error code, processing the to-be-recognized text data through a third-party natural language understanding service to obtain a third-party semantic result; and converting the third-party semantic result into a target semantic result matched with a vehicle device according to a semantic protocol conversion rule. The application can call the third-party natural language understanding service to process the to-be-recognized text data of the vehicle, convert the third-party semantic result into the target semantic result matched with the vehicle device, and effectively avoid the situation that the user request of the vehicle device cannot be responded in the related art.

Description

Technical Field

[0001] This application relates to the field of text data processing technology, and in particular to a method and apparatus for processing vehicle-mounted semantic results. Background Technology

[0002] With the rapid development of internet technology, voice signals are widely used to control the functions of terminal devices. For example, in vehicle equipment, voice signals can be used to control functions in different areas. Specifically, users input voice signals, which the vehicle equipment receives and sends to the vehicle network cloud. The voice recognition model in the vehicle network cloud then processes the voice signals to obtain semantic results.

[0003] However, the current problem is that the semantic understanding of user requests in the connected vehicle cloud faces some challenges. On the one hand, due to the limitations of existing technologies, the connected vehicle cloud may not be able to directly support the semantic understanding of user requests and needs to rely on the semantic understanding results of third parties. On the other hand, even with existing technological support, the semantic understanding results of third parties may not match the current vehicle equipment scenario, resulting in the inability to meet the user requests of the vehicle equipment, thereby reducing the user experience. Summary of the Invention

[0004] In view of this, the present application provides a method and apparatus for processing vehicle semantic results to solve the technical problem that the current driving route planning method may have certain inaccuracies due to the lack of consideration for these complex situations in the prior art.

[0005] A first aspect of this application provides a method for processing vehicle-mounted semantic results, comprising: acquiring text data to be recognized corresponding to a vehicle-mounted voice signal; determining the type of the text data to be recognized based on the text data to be recognized; when the type of the text data to be recognized is a vehicle type, processing the text data to be recognized through a local natural language understanding service to obtain a local semantic result; when the local semantic result is a preset error code, processing the text data to be recognized through a third-party natural language understanding service to obtain a third-party semantic result; and converting the third-party semantic result into a target semantic result that matches the vehicle device according to semantic protocol conversion rules.

[0006] A second aspect of this application provides an apparatus for processing vehicle-mounted semantic results, comprising: an acquisition module for acquiring text data to be recognized corresponding to a vehicle-mounted voice signal; a determination module for determining the type of the text data to be recognized based on the text data; a first recognition processing module for processing the text data to be recognized through a local natural language understanding service to obtain a local semantic result when the type of the text data to be recognized is a vehicle type; a second recognition processing module for processing the text data to be recognized through a third-party natural language understanding service to obtain a third-party semantic result when the local semantic result is a preset error code; and a conversion module for converting the third-party semantic result into a target semantic result that matches the vehicle equipment according to semantic protocol conversion rules.

[0007] A third aspect of this application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the method provided in the first aspect above.

[0008] A fourth aspect of this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the method provided in the first aspect above.

[0009] The beneficial effects of this application embodiment compared with the prior art include at least the following: This application embodiment obtains the text data to be recognized corresponding to the vehicle voice signal, and determines the type of the text data to be recognized based on the text data to be recognized. When the type of the text data to be recognized is a vehicle type, the text data to be recognized is processed by a local natural language understanding service to obtain a local semantic result. When the local semantic result is a preset error code, the text data to be recognized is processed by a third-party natural language understanding service to obtain a third-party semantic result. Then, according to the semantic protocol conversion rules, the third-party semantic result is converted into a target semantic result that matches the vehicle device. In this way, it is possible to process the text data to be recognized of the vehicle by calling a third-party natural language understanding service, and also to convert the third-party semantic result into a target semantic result that matches the vehicle device. This effectively avoids the situation in related technologies where user requests from vehicle devices cannot be responded to, and improves the user experience. Attached Figure Description

[0010] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0011] Figure 1 This is a schematic diagram of an in-vehicle semantic result processing system according to an embodiment of this application;

[0012] Figure 2 This is a flowchart of a method for processing vehicle semantic results according to an embodiment of this application;

[0013] Figure 3 This is a flowchart of another method for processing vehicle semantic results according to an embodiment of this application;

[0014] Figure 4 This is a flowchart illustrating how third-party semantic results are converted into semantic results that match the vehicle equipment, according to an embodiment of this application.

[0015] Figure 5 This is a flowchart of another method for processing vehicle semantic results according to an embodiment of this application;

[0016] Figure 6 This is a schematic diagram illustrating the conversion of third-party semantic results into semantic results that match vehicle equipment in an embodiment of this application;

[0017] Figure 7 This is a block diagram of an in-vehicle semantic result processing device according to an embodiment of this application;

[0018] Figure 8 This is a schematic diagram of the structure of an electronic device according to an embodiment of this application. Detailed Implementation

[0019] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this application with unnecessary detail.

[0020] Figure 1 This is a schematic diagram of an in-vehicle semantic result processing system according to an embodiment of this application.

[0021] like Figure 1 As shown, the system architecture 100 may include a first vehicle terminal 101, a second vehicle terminal 102, a third vehicle terminal 103, a network 104, and a server 105. The network 104 serves as the medium for providing communication links between the first vehicle terminal 101, the second vehicle terminal 102, the third vehicle terminal 103, and the server 105. The network 104 may include various connection types, such as wired or wireless communication links, or fiber optic cables, etc.

[0022] It should be understood that Figure 1The number of vehicle terminals, networks, and servers shown is merely illustrative. Depending on implementation needs, any number of vehicle terminals, networks, and servers can be included. For example, server 105 could be a server cluster composed of multiple servers.

[0023] Users can use the first vehicle terminal 101, the second vehicle terminal 102, and the third vehicle terminal 103 to interact with the server 105 via the network 104 to receive or send data, etc. The first vehicle terminal 101, the second vehicle terminal 102, and the third vehicle terminal 103 can be various electronic devices installed in the vehicle for receiving or sending data.

[0024] Server 105 can be a vehicle-to-everything (V2X) cloud providing various services. For example, server 105 can acquire in-vehicle voice signals from a first vehicle terminal 101 (or a second vehicle terminal 102 or a third vehicle terminal 103), process the in-vehicle voice signals using a voice recognition model, and identify the corresponding text data to be recognized. Based on the text data to be recognized, the type of the text data to be recognized is determined. When the type of the text data to be recognized is a vehicle type, the text data to be recognized is processed by a local natural language understanding service to obtain a local semantic result. When the local semantic result is a preset error code, the text data to be recognized is processed by a third-party natural language understanding service to obtain a third-party semantic result. Then, according to the semantic protocol conversion rules, the third-party semantic result is converted into a target semantic result that matches the vehicle equipment. In this way, it is possible to process the text data to be recognized from the vehicle by calling a third-party natural language understanding service, and also to convert the third-party semantic result into a target semantic result that matches the vehicle equipment. This improves the fault tolerance of the system in the V2X cloud, effectively avoids the situation where the system cannot respond to user requests from the vehicle equipment, and improves the user experience.

[0025] The method and apparatus for processing vehicle semantic results according to embodiments of this application will now be described in detail with reference to the accompanying drawings.

[0026] Figure 2 This is a flowchart illustrating a method for processing vehicle-mounted semantic results according to an embodiment of this application. The method provided in this application embodiment can be executed by any electronic device with computer processing capabilities, such as... Figure 1 The server shown.

[0027] like Figure 2 As shown, the method for processing vehicle semantic results includes steps S210 to S250.

[0028] In step S210, the text data to be recognized corresponding to the vehicle voice signal is obtained.

[0029] In step S220, the type of the text data to be identified is determined based on the text data to be identified.

[0030] In step S230, when the type of the text data to be identified is vehicle type, the text data to be identified is processed by the local natural language understanding service to obtain local semantic results.

[0031] In step S240, when the local semantic result is a preset error code, the text data to be identified is processed by a third-party natural language understanding service to obtain the third-party semantic result.

[0032] In step S250, the third-party semantic results are converted into target semantic results that match the vehicle equipment according to the semantic protocol conversion rules.

[0033] This method can acquire the text data to be recognized corresponding to the vehicle's voice signal, and determine the type of the text data to be recognized based on it. When the type of the text data to be recognized is a vehicle type, the text data to be recognized is processed by a local natural language understanding service to obtain a local semantic result. When the local semantic result is a preset error code, the text data to be recognized is processed by a third-party natural language understanding service to obtain a third-party semantic result. Then, according to the semantic protocol conversion rules, the third-party semantic result is converted into a target semantic result that matches the vehicle device. In this way, it is possible to process the text data to be recognized of the vehicle by calling a third-party natural language understanding service, and also to convert the third-party semantic result into a target semantic result that matches the vehicle device. This effectively avoids the situation in related technologies where user requests from vehicle devices cannot be responded to, thus improving the user experience.

[0034] In some embodiments, users in a vehicle can control different functions of the vehicle's equipment using various in-vehicle voice signals. For example, vehicle-type voice signals can be used to control the seats, air conditioning, windows, driving modes, etc., while non-vehicle-type voice signals can be used to control navigation software, video software, audio software, social media software, etc.

[0035] Based on the above embodiments, the voice recognition model in the vehicle network cloud can identify different types of in-vehicle voice signals, thereby obtaining different types of text data to be recognized. For example, there is text data related to vehicle type and text data related to non-vehicle type. Text data related to vehicle type could be phrases like "turn on the air conditioner," "turn on sport mode," "set the air conditioner temperature to the lowest setting," or "open the window." Text data related to non-vehicle type could be phrases like "set the navigation map to the maximum setting," "play rock music," "play an animated film," or "open a chat application."

[0036] In related technologies, when identifying vehicle type text data through the local natural language understanding service in the vehicle network cloud, if the local natural language understanding service malfunctions and fails to identify the vehicle type, or if identification fails during processing, it cannot support calling a third-party natural language understanding service to identify and process the vehicle type text data. Alternatively, it can support using a third-party natural language understanding service to identify and process the vehicle type text data and obtain a third-party semantic result, but it cannot convert the third-party semantic result into a semantic result that matches the vehicle device. Therefore, the method provided in this application addresses the issue where the local natural language understanding service malfunctions and fails to identify the vehicle type, resulting in a preset error code. In this case, a third-party natural language understanding service can be promptly called to identify and process the vehicle type text data and obtain a third-party semantic result. Then, through semantic protocol rules, the third-party semantic result is converted into a semantic result that matches the vehicle device. This allows the vehicle network cloud to determine the corresponding feedback text based on the semantic result, enabling the vehicle device to promptly execute the corresponding functions based on the control command corresponding to the feedback text. This effectively avoids the situation in related technologies where the vehicle device cannot respond to user requests, thus improving the user experience.

[0037] Figure 3 This is a flowchart of another method for processing vehicle semantic results according to an embodiment of this application.

[0038] like Figure 3 As shown, the method for processing vehicle semantic results also includes steps S310 and S320.

[0039] In step S310, when the type of the text data to be identified is not vehicle type, the text data to be identified is processed by a third-party natural language understanding service to obtain third-party semantic results.

[0040] In step S320, the third-party semantic results are converted into target semantic results that match the vehicle equipment according to the semantic protocol conversion rules.

[0041] This method, when dealing with non-vehicle-related text data, utilizes a third-party natural language understanding service to process the text data, obtaining a third-party semantic result. Then, based on semantic protocol conversion rules, this third-party semantic result is transformed into a target semantic result matching the vehicle's device. This approach eliminates the need for the vehicle network cloud to call its local natural language understanding service for non-vehicle-related text data; it directly utilizes the third-party service, thus improving processing efficiency. Finally, the method converts the third-party semantic result into a target semantic result matching the vehicle's device, effectively preventing situations where related technologies fail to respond to user requests from the vehicle's device, thereby enhancing user experience.

[0042] In some embodiments, when the text data to be identified that is not related to the vehicle is such as "Navigation map set to maximum", "Play rock music", "Play cartoon", "Open chat tool", etc., a third-party natural language understanding service can be directly invoked to recognize and process the text data. Based on semantic protocol conversion rules, the third-party semantic results corresponding to the text data such as "Navigation map set to maximum", "Play rock music", "Play cartoon", "Open chat tool" are converted into target semantic results that match the vehicle device.

[0043] Figure 4 This is a flowchart of another method for processing vehicle semantic results according to an embodiment of this application.

[0044] like Figure 4 As shown, the method for processing vehicle semantic results also includes steps S410 to S430.

[0045] In step S410, a protocol for parsing the semantic result is determined based on the semantic result corresponding to the third-party natural language understanding service.

[0046] In step S420, the semantic result corresponding to the third-party natural language understanding service is parsed using a protocol for parsing the semantic result, so as to obtain the third-party semantic field and the value corresponding to the third-party semantic field.

[0047] In step S430, the target semantic result matching the vehicle equipment is determined based on the third-party semantic field and the value corresponding to the third-party semantic field.

[0048] This method can determine the protocol used to parse the semantic result corresponding to the third-party natural language understanding service, and then parse the semantic result corresponding to the third-party natural language understanding service through the protocol used to parse the semantic result to obtain the third-party semantic field and its corresponding value. Then, based on the third-party semantic field and its corresponding value, the target semantic result matching the vehicle device can be determined. In this way, the third-party semantic result can be quickly and accurately converted into a semantic result matching the vehicle device.

[0049] In some embodiments, determining the protocol used to parse the semantic results based on the semantic results corresponding to a third-party natural language understanding service refers to receiving the user's voice signal in the vehicle network cloud and then calling the third-party natural language understanding service for semantic recognition processing to obtain the semantic results. To correctly parse and understand these semantic results, a protocol or specification needs to be defined to parse the semantic results and obtain the third-party semantic fields and their corresponding values. For example, the protocol used to parse the semantic results may include, but is not limited to, XML, JSON, RDF, etc. Based on the characteristics and requirements of the semantic results, the data structure of the protocol is defined. These data structures should accurately represent various information in the semantic results, including entities, attributes, relationships, etc. Furthermore, metadata can be considered to describe the source, credibility, and other information of the semantic results. The syntax and semantic rules of the protocol are determined to ensure the consistency and accuracy of the parsing process. Syntax rules define the structure and organization of each element in the protocol, while semantic rules define the meaning and interpretation of these elements. This ensures the consistency of semantic result parsing across different systems. Based on the protocol specifications, a corresponding parser is developed to parse and process the semantic results. The developed parser is integrated into a specific system or application to achieve the parsing and processing of semantic results.

[0050] Based on the foregoing embodiments, refer to Figure 6 The semantic result is parsed using a protocol for parsing third-party semantic results, yielding third-party semantic fields and their corresponding values. For example, third-party semantic fields could be "operation", "service", "semanticKey", and "semanticValue". The value corresponding to the third-party semantic field "operation" is "ZOOM_IN_MAX", the value corresponding to "service" is "mapU", the value corresponding to "semanticKey" is "insType", and the value corresponding to "semanticValue" is "ZOOM_IN_MAX".

[0051] In some embodiments, before converting third-party semantic results into target semantic results matching the vehicle, a preset mapping table needs to be configured based on the fields and field values ​​of historical third-party semantic results and the fields and field values ​​of historical local semantic results. For example, historical third-party semantic results are parsed using a protocol used to parse third-party semantic results to obtain the fields and field values ​​of the historical third-party semantic results. Historical local semantic results are parsed using a protocol used to parse local semantic results to obtain the fields and field values ​​of the historical local semantic results.

[0052] Based on the aforementioned embodiments, the semantic parsing results of historical local semantic results are as follows:

[0053] "domain": domain,

[0054] "intent": intention,

[0055] "semantic":{

[0056] "name": Device name,

[0057] "operand":{

[0058] "function": The device's function / attribute.

[0059] "action": the specific operation.

[0060] "value": The operation value of the device's function / attribute.

[0061] }

[0062] }

[0063] "subText": The requested text

[0064] }

[0065] The semantic parsing results of historical third-party semantic results are as follows:

[0066]

[0067] Based on the mapping relationship between third-party semantic understanding results and local semantic understanding results, the fields and field values ​​in historical third-party semantic results, and the fields and field values ​​in historical local semantic results, a preset mapping table is created as follows:

[0068]

[0069] The fields "operation", "service", "semanticKey", and "semanticValue" and their corresponding values ​​are parsed from historical third-party semantic results. The fields "domain", "intent", "name", "function", "action", and "value" and their corresponding values ​​are parsed from local semantic results. In this embodiment, the fields and values ​​in the historical third-party semantic results and the fields and values ​​in the local semantic results can be set according to the needs of the actual application scenario. Using the above method, the mapping relationships between all third-party semantic results and their corresponding semantic results that can be recognized by the local natural language understanding service in different scenarios can be compiled. All rule data is stored in the aforementioned preset mapping table. If data persistence is required, the protocol rules can also be loaded into the corresponding database table. When the user's semantics cannot be understood by the local natural language understanding service, the third-party natural language understanding service is invoked to obtain the corresponding result. Then, the corresponding mapping relationship record is found in the mapping table based on the protocol rules, and the corresponding local semantic result is found based on the third-party semantic result.

[0070] In some embodiments, determining the target semantic result matching the vehicle device based on the third-party semantic field and its corresponding value includes: retrieving the local semantic field matching the vehicle device and its corresponding value from a preset mapping table based on the third-party semantic field and its corresponding value; and generating the target semantic result matching the vehicle device based on the local semantic field and its corresponding value. For example, the preset mapping table is traversed based on the third-party semantic field and its corresponding value to retrieve the third-party semantic field and its corresponding value. Then, based on the mapping relationship between the third-party semantic result and the local semantic result in the preset mapping table, the local semantic field and its corresponding value are retrieved. Finally, based on the protocol supported by the vehicle device, the target semantic result matching the vehicle device is generated. See [link to relevant documentation] for details. Figure 6 This approach avoids the need for developers to create a completely new local natural language understanding service, saving time and costs, and also greatly improving the scalability of the current system.

[0071] Figure 5 This is a flowchart of another method for processing vehicle semantic results according to an embodiment of this application.

[0072] like Figure 5 As shown, the method for processing vehicle semantic results also includes steps S510 and S520.

[0073] In step S510, the protocol formats supported by the vehicle equipment are obtained.

[0074] In step S520, a target semantic result in protocol format is generated based on the local semantic field and its corresponding value.

[0075] This method can obtain the protocol formats supported by the vehicle equipment, and generate the target semantic result of the protocol format based on the local semantic fields and their corresponding values. In this way, the semantic result of the protocol supported by the vehicle equipment can be generated by converting the local semantic fields and their corresponding values ​​based on the third-party semantic fields and their corresponding values. This can avoid the situation where the semantic result is incompatible with the vehicle equipment and further improve the user experience.

[0076] In some embodiments, determining the type of the text data to be identified, based on the text data to be identified, includes: extracting entity words from the text data to be identified; determining whether the entity words are related to vehicle equipment; if the entity words are related to vehicle equipment, determining the type of the text data to be identified as vehicle type; if the entity words are not related to vehicle equipment, determining the type of the text data to be identified as non-vehicle type. For example, entity words can be extracted from historical text data to be identified using methods such as word segmentation and part-of-speech tagging. Entity words are words with specific meanings in the text, such as "vehicle," "engine," "driver," "navigation," "cartoon," "song title," etc. Determining the relevance of entity words to vehicle equipment: For each extracted entity word, a determination of its relevance to vehicle equipment is made. This can be done using methods such as dictionaries, keyword matching, and semantic similarity calculation. If the entity word is related to vehicle equipment, the type of the text data to be identified can be determined as vehicle type; if the entity word is not related to vehicle equipment, the type of the text data to be identified is determined as non-vehicle type. Based on the judgment result of each entity word, the number of judgment results is counted. If there are entity words related to vehicle equipment, the type of the text data to be identified is determined to be vehicle type; if all entity words are not related to vehicle equipment, the type of the text data to be identified is determined to be non-vehicle type.

[0077] In some embodiments, the method further includes: determining text data for feedback to the vehicle device based on a target semantic result matching the vehicle device; generating control instructions for the vehicle device based on the text data for feedback, and sending the control instructions to the vehicle device so that the vehicle device performs corresponding operations according to the control instructions. For example, converting the text data fed back to the vehicle device into control instructions that can be understood and executed by the vehicle device can be achieved by using a specific control instruction format or protocol. For example, if the vehicle device uses a specific communication protocol (such as the CAN bus protocol), the text data can be converted into a control instruction format that conforms to the protocol to ensure that the vehicle device can correctly parse and execute the instructions. In this way, the text data can be converted into control instructions that the vehicle device can parse, thereby enabling the vehicle device to respond to user requests in a timely manner.

[0078] Figure 7 This is a block diagram of an in-vehicle semantic result processing device according to an embodiment of this application.

[0079] like Figure 7 As shown, the vehicle-mounted semantic result processing device 700 includes an acquisition module 710, a determination module 720, a first recognition processing module 730, a second recognition processing module 740, and a conversion module 750.

[0080] Specifically, the acquisition module 710 is used to acquire the text data to be recognized corresponding to the vehicle voice signal.

[0081] The determination module 720 is used to determine the type of the text data to be recognized based on the text data to be recognized.

[0082] The first recognition processing module 730 is used to process the text data to be recognized through local natural language understanding service when the type of the text data to be recognized is vehicle type, and obtain local semantic results.

[0083] The second recognition and processing module 740 is used to process the text data to be recognized through a third-party natural language understanding service to obtain the third-party semantic result when the local semantic result is a preset error code.

[0084] The conversion module 750 is used to convert third-party semantic results into target semantic results that match the vehicle equipment according to the semantic protocol conversion rules.

[0085] The vehicle-mounted semantic result processing device 700 can acquire the text data to be recognized corresponding to the vehicle-mounted voice signal, and determine the type of the text data to be recognized based on the text data. When the type of the text data to be recognized is a vehicle type, the text data to be recognized is processed by a local natural language understanding service to obtain a local semantic result. When the local semantic result is a preset error code, the text data to be recognized is processed by a third-party natural language understanding service to obtain a third-party semantic result. Then, according to the semantic protocol conversion rules, the third-party semantic result is converted into a target semantic result that matches the vehicle device. In this way, it is possible to process the text data to be recognized of the vehicle by calling a third-party natural language understanding service, and also to convert the third-party semantic result into a target semantic result that matches the vehicle device. This effectively avoids the situation in related technologies where user requests from vehicle devices cannot be responded to, and improves the user experience.

[0086] In some embodiments, the vehicle semantic result processing device 700 is further configured to: when the type of the text data to be identified is not a vehicle type, identify and process the text data to be identified through a third-party natural language understanding service to obtain a third-party semantic result; and convert the third-party semantic result into a target semantic result that matches the vehicle equipment according to the semantic protocol conversion rules.

[0087] In some embodiments, the conversion module 450 is configured to: determine a protocol for parsing the semantic result based on the semantic result corresponding to the third-party natural language understanding service; parse the semantic result corresponding to the third-party natural language understanding service using the protocol for parsing the semantic result to obtain the third-party semantic field and the value corresponding to the third-party semantic field; and determine a target semantic result that matches the vehicle device based on the third-party semantic field and the value corresponding to the third-party semantic field.

[0088] In some embodiments, determining the target semantic result matching the vehicle device based on the third-party semantic field and its corresponding value includes: obtaining the local semantic field matching the vehicle device and its corresponding value from a preset mapping table based on the third-party semantic field and its corresponding value; and generating the target semantic result matching the vehicle device based on the local semantic field and its corresponding value.

[0089] In some embodiments, generating a target semantic result that matches the vehicle device based on the local semantic field and its corresponding value includes: obtaining the protocol format supported by the vehicle device; and generating a target semantic result of the protocol format based on the local semantic field and its corresponding value.

[0090] In some embodiments, the determining module 720 is configured to: extract entity words from the text data to be identified based on the text data to be identified; determine whether the entity words are related to vehicle equipment; if the entity words are related to vehicle equipment, determine that the type of the text data to be identified is vehicle type; if the entity words are not related to vehicle equipment, determine that the type of the text data to be identified is non-vehicle type.

[0091] In some embodiments, the vehicle semantic result processing device 700 is further configured to: determine text data for feedback to the vehicle device based on the target semantic result matching the vehicle device; generate control instructions for the vehicle device based on the text data for feedback to the vehicle device; and send the control instructions to the vehicle device so that the vehicle device performs corresponding operations according to the control instructions.

[0092] Figure 8 This is a schematic diagram of the structure of an electronic device according to an embodiment of this application, such as... Figure 8 As shown, the electronic device 800 of this embodiment includes a processor 810, a memory 820, and a computer program 830 stored in the memory 820 and executable on the processor 810. When the processor 810 executes the computer program 830, it implements the steps in the various method embodiments described above. Alternatively, when the processor 810 executes the computer program 830, it implements the functions of each module in the various device embodiments described above.

[0093] Electronic device 800 can be a desktop computer, laptop, handheld computer, cloud server, or other electronic device. Electronic device 800 may include, but is not limited to, processor 810 and memory 820. Those skilled in the art will understand that... Figure 8 This is merely an example of electronic device 800 and does not constitute a limitation on electronic device 800. It may include more or fewer components than shown, or different components.

[0094] The processor 810 can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.

[0095] The memory 820 can be an internal storage unit of the electronic device 800, such as a hard disk or RAM of the electronic device 800. The memory 820 can also be an external storage device of the electronic device 800, such as a plug-in hard disk, Smart Media Card (SMC), Secure Digital (SD) card, or Flash Card equipped on the electronic device 800. The memory 820 can also include both internal and external storage units of the electronic device 800. The memory 820 is used to store computer programs and other programs and data required by the electronic device.

[0096] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0097] If an integrated module is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program may include computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. A computer-readable medium may include: any entity or device capable of carrying computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc. It should be noted that the content included in a computer-readable medium can be appropriately added to or subtracted according to the requirements of legislation and patent practice in a jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electrical carrier signals and telecommunication signals.

[0098] The above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A method for processing vehicle-mounted semantic results, characterized in that, include: Acquire the text data to be recognized corresponding to the vehicle's voice signal; Based on the text data to be identified, determine the type of the text data to be identified; When the type of the text data to be identified is a vehicle type, the text data to be identified is processed by the local natural language understanding service to obtain a local semantic result. When the local semantic result is a preset error code, the text data to be identified is processed by a third-party natural language understanding service to obtain a third-party semantic result; According to the semantic protocol conversion rules, a preset mapping table is searched to convert the third-party semantic results into target semantic results that match the vehicle equipment. Before searching the preset mapping table according to the semantic protocol conversion rules, the method further includes: Based on the mapping relationship between third-party semantic results and local semantic results, the fields and field values ​​in historical third-party semantic results, and the fields and field values ​​in historical local semantic results, the preset mapping table is created; The step of searching a preset mapping table according to semantic protocol conversion rules and converting the third-party semantic result into a target semantic result that matches the vehicle equipment includes: According to the semantic protocol conversion rules, the third-party semantic results are parsed to obtain the third-party semantic fields and their corresponding values; Based on the third-party semantic field and its corresponding value, obtain the local semantic field that matches the vehicle device and its corresponding value from the preset mapping table; Based on the local semantic field and its corresponding value, a target semantic result in the protocol format supported by the vehicle device is generated.

2. The method for processing vehicle semantic results according to claim 1, characterized in that, The method further includes: When the type of the text data to be identified is not vehicle type, the text data to be identified is processed by the third-party natural language understanding service to obtain the third-party semantic result; According to the semantic protocol conversion rules, the third-party semantic results are converted into target semantic results that match the vehicle equipment.

3. The method for processing vehicle semantic results according to claim 1, characterized in that, Based on the text data to be identified, determining the type of the text data to be identified includes: Based on the text data to be identified, extract entity words from the text data to be identified; Determine whether the entity word is related to the vehicle equipment. If the entity word is related to the vehicle equipment, determine that the type of the text data to be identified is the vehicle type. If the entity word is not related to the vehicle equipment, determine that the type of the text data to be identified is a non-vehicle type.

4. The method for processing vehicle semantic results according to any one of claims 1 to 3, characterized in that, The method also includes: Based on the target semantic results that match the vehicle equipment, determine the text data used to provide feedback to the vehicle equipment; Based on the text data used to provide feedback to the vehicle equipment, control commands for the vehicle equipment are generated and sent to the vehicle equipment so that the vehicle equipment can perform corresponding operations according to the control commands.

5. A vehicle-mounted semantic result processing device, characterized in that, include: The acquisition module is used to acquire the text data to be recognized corresponding to the vehicle voice signal; The determining module is used to determine the type of the text data to be identified based on the text data to be identified; The first recognition processing module is used to recognize and process the text data to be recognized through a local natural language understanding service to obtain a local semantic result when the type of the text data to be recognized is a vehicle type. The second recognition and processing module is used to process the text data to be recognized through a third-party natural language understanding service to obtain a third-party semantic result when the local semantic result is a preset error code. The conversion module is used to look up a preset mapping table according to the semantic protocol conversion rules and convert the third-party semantic results into target semantic results that match the vehicle equipment. The conversion module is also used to: create the preset mapping table based on the mapping relationship between third-party semantic results and local semantic results, the fields and field values ​​in historical third-party semantic results, and the fields and field values ​​in historical local semantic results; The conversion module is further configured to: parse the third-party semantic result according to the semantic protocol conversion rules to obtain the third-party semantic field and the value corresponding to the third-party semantic field; and obtain the local semantic field matching the vehicle equipment and the value corresponding to the local semantic field from a preset mapping table according to the third-party semantic field and the value corresponding to the third-party semantic field. Based on the local semantic field and its corresponding value, a target semantic result in the protocol format supported by the vehicle device is generated.

6. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes a computer program, it implements the steps of any one of claims 1 to 4.

7. A computer-readable storage medium storing a computer program, characterized in that, When a computer program is executed by a processor, it implements the steps of any one of claims 1 to 4.

Images