Method, device and storage medium for multi-round in-vehicle voice interaction

Abstract

The present application relates to the technical field of vehicle-mounted voice interaction, and discloses a method, device, and storage medium for vehicle-mounted voice multi-round interaction, the method comprising: determining to enter the vehicle-mounted voice multi-round interaction process; executing the adjudication process to obtain the judgment result when the duration meets the preset conditions; and executing the action corresponding to the judgment result according to the judgment result. It can ensure that the user's complete intention is obtained, thereby achieving complete interaction and improving the user's experience.

Description

Technical Field

[0001] The present invention relates to the field of vehicle-mounted voice interaction technology, and in particular to a method and device, and a storage medium for vehicle-mounted voice multi-round interaction. Background Art

[0002] With the popularization and development of in-car voice, the use of in-car voice in cars is a new and rapidly spreading model. In particular, voice makes human-computer interaction easier and more frequent. Therefore, how to more reasonably obtain the user's intention to achieve a complete interaction is what every voice interaction company pursues.

[0003] In multi-round interactions, the current existing methods mostly set a countdown and exit the multi-round interaction when the countdown ends. However, this may cause the user to not have enough time to input the complete intention, which brings the user an unsatisfactory interactive experience. Summary of the invention

[0004] The technical problem to be solved by the present invention is to provide a method, device and storage medium for multi-round in-vehicle voice interaction, which can ensure that the user's complete intention is obtained, thereby achieving complete interaction and improving the user's experience.

[0005] In order to solve the above technical problems, the first aspect of the present invention discloses a method for multi-round in-vehicle voice interaction, comprising:

[0006] Determine to enter the multi-round interaction process of in-vehicle voice;

[0007] When the duration meets the preset conditions, the adjudication process is executed to obtain the judgment result;

[0008] According to the judgment result, an action corresponding to the judgment result is executed.

[0009] Optionally, the duration meets a preset condition, including:

[0010] The remaining duration of the multi-round interaction process is less than or equal to the first preset duration;

[0011] and / or,

[0012] The duration of entering the multi-round interaction process is greater than or equal to the second preset duration.

[0013] Optionally, before executing the arbitration judgment process and obtaining the judgment result, the method further includes: determining a target vertical category from a plurality of preset vertical categories;

[0014] The execution ruling judgment process obtains the judgment result, including:

[0015] Determine a judgment result according to the first judgment indicator, the second judgment indicator, and the third judgment indicator;

[0016] Among them, the first judgment indicator is the audio energy value, the second judgment indicator is the final intention, and the third judgment indicator is the result interaction of the target vertical category.

[0017] Optionally, determining the judgment result according to the first judgment indicator, the second judgment indicator, and the third judgment indicator includes:

[0018] Detecting whether the current audio energy value is within the range of human voice, and if not, determining that the judgment result is the first result;

[0019] If the current audio energy value is within the range of human utterance, automatic speech recognition is performed to determine whether there is a final semantic intention and whether the result interaction of the target vertical category has been entered;

[0020] If there is a final semantic intention and the result interaction of the target vertical category has been entered, the judgment result is determined to be the second result;

[0021] If there is no final semantic intention and the result interaction of the target vertical category has not been entered, the judgment result is determined to be the third result.

[0022] Optionally, the executing the adjudication judgment process to obtain the judgment result includes:

[0023] Determining a judgment result according to the first judgment indicator and the second judgment indicator;

[0024] The first judgment index is the audio energy value, and the second judgment index is the final intention.

[0025] Optionally, determining the judgment result according to the first judgment indicator and the second judgment indicator includes:

[0026] Detecting whether the current audio energy value is within the range of human voice, and if not, determining that the judgment result is the first result;

[0027] If the current audio energy value is within the range of human utterance, automatic speech recognition is performed to determine whether there is a semantic final intention;

[0028] If there is a final semantic intention, the judgment result is determined to be the second result;

[0029] If there is no final semantic intention, the judgment result is determined to be the third result.

[0030] Optionally, the performing an action corresponding to the judgment result according to the judgment result includes:

[0031] If the result is determined to be the first result or the second result, exit the interaction;

[0032] When the judgment result is the third result, the interaction is exited after the third preset time period.

[0033] A second aspect of the present invention discloses a device for multi-round in-vehicle voice interaction, the device comprising:

[0034] A determination module, used to determine the entry into the multi-round vehicle voice interaction process;

[0035] A judgment module, used to execute the judgment process and obtain the judgment result when the duration meets the preset conditions;

[0036] An execution module is used to execute an action corresponding to the judgment result according to the judgment result.

[0037] The third aspect of the present invention discloses another device for multi-round in-vehicle voice interaction, the device comprising:

[0038] A memory storing executable program code;

[0039] a processor coupled to the memory;

[0040] The processor calls the executable program code stored in the memory to execute the method for multi-round in-vehicle voice interaction disclosed in the first aspect of the present invention.

[0041] The fourth aspect of the present invention discloses a computer-readable storage medium, which stores computer instructions. When the computer instructions are called, they are used to execute the method for multi-round in-vehicle voice interaction disclosed in the first aspect of the present invention.

[0042] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0043] In an embodiment of the present invention, by determining to enter a multi-round in-vehicle voice interaction process, when the duration meets a preset condition, a ruling judgment process is executed to obtain a judgment result; based on the judgment result, an action corresponding to the judgment result is executed, thereby ensuring that the user's complete intention is obtained, thereby achieving complete interaction and improving the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0045] Figure 1 It is a flowchart of a method for multi-round in-vehicle voice interaction disclosed in an embodiment of the present invention;

[0046] Figure 2 It is a flowchart diagram of another method for multi-round in-vehicle voice interaction disclosed in an embodiment of the present invention;

[0047] Figure 3 It is a structural schematic diagram of a device for multi-round in-vehicle voice interaction disclosed in an embodiment of the present invention;

[0048] Figure 4 It is a structural schematic diagram of another device for multi-round in-vehicle voice interaction disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0049] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0050] The terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish different objects rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, device, product or end including a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units that are not listed, or may optionally include other steps or units inherent to these processes, methods, products or ends.

[0051] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0052] Embodiment 1

[0053] See also Figure 1 , Figure 1 FIG. 1 is a flow chart of a method for multi-round in-vehicle voice interaction disclosed in an embodiment of the present invention. Figure 1 As shown, the method for multi-round in-vehicle voice interaction may include:

[0054] Step 101: Determine to enter the in-vehicle voice multi-round interaction process.

[0055] Step 102: When the duration meets the preset conditions, the decision-making process is executed to obtain a decision result.

[0056] Step 103: According to the judgment result, execute an action corresponding to the judgment result.

[0057] Optionally, the duration meets a preset condition, including: the remaining duration of the multi-round interaction process is less than or equal to the first preset duration. In this way, the final decision is made at the end of the countdown.

[0058] Optionally, the duration meets a preset condition, including: the duration of entering the multi-round interaction process is greater than or equal to a second preset duration. In this way, after entering the multi-round interaction process for a long enough time, the final decision is made.

[0059] Preferably, the first preset duration is 3 seconds.

[0060] Preferably, the second preset duration is 6 seconds.

[0061] Optionally, before executing the decision judgment process and obtaining the judgment result, the method further includes: determining the target vertical category from a plurality of preset vertical categories; executing the decision judgment process and obtaining the judgment result, including: determining the judgment result according to the first judgment indicator, the second judgment indicator, and the third judgment indicator; wherein the first judgment indicator is the audio energy value, the second judgment indicator is the final intention, and the third judgment indicator is the result interaction of the target vertical category. In this way, a specific method for executing the decision judgment process and obtaining the judgment result is given.

[0062] In an optional embodiment, the preset multiple vertical categories are: telephone, navigation, weather, vehicle control, and application.

[0063] Optionally, the judgment result is determined according to the first judgment indicator, the second judgment indicator, and the third judgment indicator, including: detecting whether the current audio energy value is within the human vocal range, if not, determining the judgment result to be the first result; if the current audio energy value is within the human vocal range, performing automatic speech recognition to determine whether there is a semantic final intention, and whether it has entered the result interaction of the target vertical category; if there is a semantic final intention, and it has entered the result interaction of the target vertical category, then determining the judgment result to be the second result; if there is no semantic final intention, and it has not entered the result interaction of the target vertical category, then determining the judgment result to be the third result. In this way, a specific method for determining the judgment result according to the judgment indicator is given.

[0064] In the embodiment of the present disclosure, the method for determining whether there is a semantic final intention can be: using automatic speech recognition to obtain the complete audio content, and then searching a preset model or database to see if there is a corresponding intention. If it can be retrieved, it means that there is a final intention.

[0065] In the embodiment of the present disclosure, in the result interaction of the target vertical category, for example, if the target vertical category is phone, the result interaction of the target vertical category is: the call is already being made or the call is already connected. For another example, if the target vertical category is navigation, the result interaction of the target vertical category is: the navigation scene has begun to plan the route or is already in the navigation process.

[0066] Optionally, executing the adjudication and judgment process to obtain a judgment result includes: determining the judgment result according to a first judgment indicator and a second judgment indicator; wherein the first judgment indicator is the audio energy value, and the second judgment indicator is the final intention.

[0067] Optionally, the judgment result is determined based on the first judgment indicator and the second judgment indicator, including: detecting whether the current audio energy value is within the human vocal range, and if not, determining the judgment result to be the first result; if the current audio energy value is within the human vocal range, performing automatic speech recognition to determine whether there is a semantic final intention; if there is a semantic final intention, determining the judgment result to be the second result; if there is no semantic final intention, determining the judgment result to be the third result.

[0068] Optionally, according to the judgment result, an action corresponding to the judgment result is performed, including: if the judgment result is the first result or the second result, exit the interaction; if the judgment result is the third result, exit the interaction after a third preset time. In this way, if the judgment result is the first result or the second result, it means that the interaction has been completed, then exit the interaction; if the judgment result is the third result, it means that the last interaction has not been completed and the interaction time needs to be extended, and the extended time is the third preset time.

[0069] Preferably, the third preset time length is 5 seconds.

[0070] The method for multi-round in-vehicle voice interaction provided by the embodiment of the present disclosure can ensure that the user's complete intention is obtained, thereby achieving complete interaction and improving the user's experience.

[0071] Embodiment 2

[0072] See also Figure 2 , Figure 2 FIG. 1 is a flow chart of another method for multi-round in-vehicle voice interaction disclosed in an embodiment of the present invention. Figure 2 As shown, the method for multi-round in-vehicle voice interaction may include:

[0073] Step 201: Determine to enter the in-vehicle voice multi-round interaction process.

[0074] Step 202: determine the target vertical category from multiple preset vertical categories.

[0075] Step 203: When the duration meets the preset conditions, the decision-making process is executed to obtain a decision result.

[0076] Step 204: According to the judgment result, execute an action corresponding to the judgment result.

[0077] The method for multi-round in-vehicle voice interaction provided by the embodiment of the present disclosure can ensure that the user's complete intention is obtained, thereby achieving complete interaction and improving the user's experience.

[0078] Embodiment 3

[0079] See also Figure 3 , Figure 3 Schematic diagram of a structure of a device for multi-round voice interaction in a vehicle disclosed in an embodiment of the present invention. Figure 3 As shown, the device may include:

[0080] A determination module 301 is used to determine whether to enter a multi-round vehicle voice interaction process;

[0081] The judgment module 302 is used to execute the judgment process and obtain the judgment result when the duration meets the preset conditions;

[0082] The execution module 303 is used to execute an action corresponding to the judgment result according to the judgment result.

[0083] It can be seen that the implementation of the present invention can ensure that the user's complete intention is obtained through the cooperation of the determination module, the judgment module, and the execution module, thereby achieving complete interaction and improving the user's usage experience.

[0084] Embodiment 4

[0085] See also Figure 4 , Figure 4 FIG. 1 is a schematic diagram of another structure of a device for multi-round in-vehicle voice interaction disclosed in an embodiment of the present invention. Figure 4 As shown, the device may include:

[0086] A memory 601 storing executable program codes;

[0087] a processor 602 coupled to the memory 601;

[0088] The processor 602 calls the executable program code stored in the memory 601 to execute the steps in the method for multi-round in-vehicle voice interaction described in the aforementioned embodiment of the present invention.

[0089] Embodiment 5

[0090] An embodiment of the present invention discloses a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to enable a computer to execute the steps of the method for multi-round in-vehicle voice interaction described in the above embodiment.

[0091] The device embodiments described above are only illustrative, wherein the modules described as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical modules, i.e., they may be located in one place, or they may be distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Those of ordinary skill in the art may understand and implement it without creative work.

[0092] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0093] Through the specific description of the above embodiments, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on such an understanding, the above technical solution can be essentially or partly contributed to the prior art in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, and the storage medium includes a read-only memory (ROM), a random access memory (RAM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), a one-time programmable read-only memory (OTPROM), an electronically erasable rewritable read-only memory (EEPROM), a compact disc (CD-ROM) or other optical disc storage, a magnetic disk storage, a magnetic tape storage, or any other computer-readable medium that can be used to carry or store data.

[0094] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of indicators includes not only those indicators, but also other indicators not explicitly listed, or indicators inherent to such process, method, commodity or device. In the absence of further restrictions, an indicator defined by the sentence "including a ..." does not exclude the existence of other identical indicators in the process, method, commodity or device including the indicator.

[0095] Finally, it should be noted that the method, device, and storage medium for multi-round in-vehicle voice interaction disclosed in the embodiments of the present invention are only preferred embodiments of the present invention, and are only used to illustrate the technical solution of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features thereof may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A method for multi-round voice interaction in a vehicle, characterized in that: The method comprises: Determine to enter the multi-round interaction process of in-vehicle voice; When the duration meets the preset conditions, the adjudication process is executed to obtain the judgment result; According to the judgment result, executing an action corresponding to the judgment result; Before the judgment result is obtained during the execution of the arbitration judgment process, the method further includes: determining a target vertical category from a plurality of preset vertical categories; The execution ruling judgment process obtains the judgment result, including: Determine a judgment result according to the first judgment indicator, the second judgment indicator, and the third judgment indicator; Among them, the first judgment indicator is the audio energy value, the second judgment indicator is the final intention, and the third judgment indicator is the result interaction of the target vertical category; Determining the judgment result according to the first judgment indicator, the second judgment indicator, and the third judgment indicator includes: Detecting whether the current audio energy value is within the range of human voice, and if not, determining that the judgment result is the first result; If the current audio energy value is within the range of human utterance, automatic speech recognition is performed to determine whether there is a final semantic intention and whether the result interaction of the target vertical category has been entered; If there is a final semantic intention and the result interaction of the target vertical category has been entered, the judgment result is determined to be the second result; If there is no final semantic intention and the result interaction of the target vertical category has not been entered, the judgment result is determined to be the third result; The performing of an action corresponding to the judgment result according to the judgment result includes: If the result is determined to be the first result or the second result, exit the interaction; When the judgment result is the third result, the interaction is exited after the third preset time period.

2. The method according to claim 1, characterized in that The duration meets the preset conditions, including: The remaining duration of the multi-round interaction process is less than or equal to the first preset duration; and / or, The duration of entering the multi-round interaction process is greater than or equal to the second preset duration.

3. A device for multi-round voice interaction in a vehicle, characterized in that: The device comprises: A determination module, used to determine the entry into the multi-round vehicle voice interaction process; A target vertical category determination module, used to determine a target vertical category from a plurality of preset vertical categories; A judgment module, used to execute a judgment process to obtain a judgment result when the duration meets a preset condition, including: determining the judgment result according to a first judgment indicator, a second judgment indicator, and a third judgment indicator; Among them, the first judgment indicator is the audio energy value, the second judgment indicator is the final intention, and the third judgment indicator is the result interaction of the target vertical category; Determining the judgment result according to the first judgment indicator, the second judgment indicator, and the third judgment indicator includes: Detecting whether the current audio energy value is within the range of human voice, and if not, determining that the judgment result is the first result; If the current audio energy value is within the range of human utterance, automatic speech recognition is performed to determine whether there is a final semantic intention and whether the result interaction of the target vertical category has been entered; If there is a final semantic intention and the result interaction of the target vertical category has been entered, the judgment result is determined to be the second result; If there is no final semantic intention and the result interaction of the target vertical category has not been entered, the judgment result is determined to be the third result; An execution module, used to execute an action corresponding to the judgment result according to the judgment result, including: If the result is determined to be the first result or the second result, exit the interaction; When the judgment result is the third result, the interaction is exited after the third preset time period.

4. A device for multi-round voice interaction in a vehicle, characterized in that: The device comprises: A memory storing executable program code; a processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the method for multi-round in-vehicle voice interaction as described in any one of claims 1-2.

5. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, which, when called, are used to execute the method for in-vehicle voice multi-round interaction as described in any one of claims 1-2.

Images