Vehicle-mounted voice control instruction library generalization method, vehicle machine and storage medium

Abstract

The invention provides a vehicle-mounted voice control instruction library generalization method, a vehicle machine and a storage medium, and relates to the technical field of vehicles. The method comprises the following steps: when it is determined that a preset voice control instruction library does not contain first text data, searching second text data associated with second voice data input by each user in the next round historically after the first voice data is input from a preset text database; under the condition that the number of the second text data is larger than a set number threshold value, standard semantic texts corresponding to all kinds of second text data are sent to the vehicle-mounted terminal to be displayed; receiving a standard semantic text selected by a user in the vehicle-mounted terminal; and if the proportion of the number of times that the selected standard semantic text is selected to the number of times that all the standard semantic texts are selected is greater than a set proportion threshold value, establishing an association relationship between the first text data and a vehicle control instruction associated with the selected standard semantic text, and adding the association relationship to a voice control instruction library.

Description

Technical Field

[0001] The present application relates to the field of vehicle technology, and in particular to a vehicle-mounted voice control instruction library generalization method, a vehicle computer, and a storage medium. Background Art

[0002] With the advancement of technology, smart cockpit systems are rapidly becoming increasingly intelligent. In-vehicle voice assistants are a convenient piece of intelligent software that enables the vehicle's smart cockpit to perform voice control functions. This means that the vehicle can monitor user voice data and convert it into text. Then, based on the vehicle control commands corresponding to the text data, the vehicle is controlled to perform functions. For example, if the user inputs the voice data "turn on the air conditioner," the vehicle converts the voice data "turn on the air conditioner" into the text data "turn on the air conditioner," then searches for the vehicle control command corresponding to the text data "turn on the air conditioner," and controls the vehicle to turn on the air conditioner based on the searched vehicle control command. Another example is if the user inputs the voice data "play music," the vehicle converts the voice data "play music" into the text data "play music," then searches for the vehicle control command corresponding to the text data "play music," and controls the vehicle to turn on the air conditioner based on the searched vehicle control command.

[0003] However, for some daily text data (for example, "The weather is so hot" or "I'm so stuffy"), the vehicle cannot find the corresponding vehicle control instructions, resulting in the vehicle only being able to reply to the customer "I haven't learned this knowledge yet", which fails to meet the user's needs for vehicle functions and has poor reliability. Summary of the Invention

[0004] The present application provides a vehicle-mounted voice control command library generalization method, a vehicle computer and a storage medium, which are used to solve the problem in the prior art that for some daily text data, the vehicle cannot find the corresponding vehicle control instructions, resulting in the inability to meet user needs for vehicle functions and poor reliability.

[0005] In a first aspect, the present application provides a method for generalizing a vehicle-mounted voice control instruction library, which is applied to a cloud server that is communicatively connected to a vehicle's head unit. The method provided by the present application includes:

[0006] receiving first voice data sent by a user monitored by the vehicle computer, and converting the first voice data into first text data;

[0007] If it is determined that the preset voice control instruction library does not contain the first text data, searching a preset text database for second text data associated with second voice data input by each user in a subsequent round after inputting the first voice data, where the second text data belongs to the voice control instruction library;

[0008] When the amount of the second text data is greater than a set amount threshold, the standard semantic text corresponding to each type of the second text data is sent to the vehicle computer for display, wherein the semantic similarity of the second text data of the same type is greater than a set similarity threshold;

[0009] receiving a standard semantic text selected by a user on the vehicle computer, wherein the vehicle computer controls the vehicle to execute a vehicle function according to a vehicle control instruction associated with the selected standard semantic text;

[0010] If the ratio of the number of times the selected standard semantic text is selected to the number of times all standard semantic texts are selected is greater than a set ratio threshold, an association relationship is established between the first text data and the vehicle control instruction associated with the selected standard semantic text, and the association relationship is added to the voice control instruction library.

[0011] In some embodiments, after converting the first voice data into the first text data, the method provided by the present application further includes:

[0012] When it is determined that the preset voice control instruction library contains the first text data, the vehicle is controlled to execute a vehicle function corresponding to the vehicle control instruction associated with the first text data.

[0013] In some implementations, sending the standard semantic text corresponding to each type of second text data to the vehicle computer display includes:

[0014] Sorting the standard semantic texts corresponding to each type of second text data according to the number of times each type of second text data has been selected in the past, wherein the standard semantic text corresponding to a type of second text data having a greater number of selections is ranked higher;

[0015] The sorted standard semantic text is sent to the vehicle computer display.

[0016] In some implementations, sending the standard semantic text corresponding to each type of second text data to the vehicle computer display includes:

[0017] Determining semantic similarity between each second text data;

[0018] Classifying a group of second text data whose semantic similarities are greater than a set semantic similarity threshold into one category;

[0019] Searching for a standard semantic text corresponding to each type of second text data from a preset semantic database;

[0020] The standard semantic text corresponding to each type of second text data is sent to the vehicle computer display.

[0021] In some embodiments, the method provided in the present application further includes: when the amount of the second text data is less than or equal to a set amount threshold, controlling the vehicle computer to play a prompt message for instructing to input clearer voice data.

[0022] In some embodiments, the method provided in the present application further includes: when the amount of the second text data is greater than a set amount threshold, controlling the vehicle computer to play a prompt message indicating that the user's function control intention cannot be understood.

[0023] In some embodiments, the ratio threshold value ranges from 70% to 90%.

[0024] The present application provides a method for generalizing an in-vehicle voice control instruction library, a vehicle computer, and a storage medium. When it is determined that a preset voice control instruction library does not contain first text data, this indicates that the vehicle is temporarily unable to understand how to execute a vehicle function using the first text data. Furthermore, the vehicle can search a preset text database for second text data associated with second voice data input by each user in the subsequent round following the first voice data input, where the second text data belongs to the voice control instruction library. It is understandable that because the first and second voice data are adjacent and strongly associated with the first voice data, the vehicle control instructions associated with the second text data are likely also associated with the first text data. When the amount of second text data exceeds a set threshold, standard semantic text corresponding to each type of second text data is sent to the vehicle computer for display, where the semantic similarity of the same type of second text data exceeds a set similarity threshold. The vehicle computer receives a standard semantic text selected by the user on the vehicle computer, where the vehicle computer controls the vehicle to execute the vehicle function based on the vehicle control instructions associated with the selected standard semantic text. If the ratio of the number of times the selected standard semantic text is selected to the number of times all standard semantic texts are selected is greater than the set ratio threshold, it means that a type of second text data corresponding to the selected standard semantic text is associated with the first text data. In this way, an association relationship is established between the first text data and the vehicle control instructions associated with the selected standard semantic text, and the association relationship is added to the voice control instruction library. When the user inputs the first voice data again next time, the vehicle control instructions can be directly found based on the first text data corresponding to the first voice data, and the vehicle can be controlled to perform vehicle functions based on the vehicle control instructions. In this way, the vehicle can self-learn the number of daily texts input by the user, and based on the daily text data, the vehicle can find the corresponding vehicle control instructions, which can automatically meet the user's needs for vehicle functions, with high reliability and good user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0026] Figure 1 A schematic diagram of the interaction between the cloud server and the vehicle provided in an embodiment of the present application;

[0027] Figure 2 A flowchart of a method for generalizing a vehicle-mounted voice control instruction library provided in an embodiment of the present application;

[0028] Figure 3 This is a functional module block diagram of the vehicle-mounted voice control instruction library generalization device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0029] Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. However, it should be understood that these descriptions are merely illustrative and are not intended to limit the scope of the present disclosure. In addition, in the following description, descriptions of well-known structures and technologies are omitted to avoid unnecessary confusion of the concepts of the present disclosure.

[0030] The accompanying drawings illustrate various schematic diagrams of structures according to embodiments of the present disclosure. These figures are not drawn to scale, and for the purpose of clarity, certain details are exaggerated and certain details may be omitted. The shapes of the various regions and layers shown in the figures, as well as their relative sizes and positional relationships, are merely exemplary and may deviate in practice due to manufacturing tolerances or technical limitations. Those skilled in the art may design regions / layers with different shapes, sizes, and relative positions as needed.

[0031] In the context of the present disclosure, when a layer / element is referred to as being "on" another layer / element, it can be directly on the other layer / element or an intervening layer / element may be present therebetween. In addition, if a layer / element is "on" another layer / element in one orientation, it may be "below" the other layer / element when the orientation is reversed.

[0032] The following describes in detail the technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0033] The embodiment of the present application provides a method for generalizing a vehicle-mounted voice control instruction library, which is applied to a cloud server, such as Figure 1 As shown, the cloud server is connected to the vehicle's head unit, where the head unit is equipped with a voice assistant. Figure 2 As shown, the method provided in the embodiment of the present application includes:

[0034] S201: Receive first voice data emitted by a user monitored by the vehicle computer, and convert the first voice data into first text data.

[0035] For example, after being woken up by the user, the voice assistant may listen to the user's first voice data, which may be "I feel stuffy." The first text data converted to it is also "I feel stuffy." For another example, after being woken up by the user, the voice assistant may listen to the user's first voice data, which may be "Turn on the air conditioner." The first text data converted to it is also "Turn on the air conditioner."

[0036] S202: Determine whether the preset voice control instruction library contains the first text data. If yes, execute S203; if not, execute S204.

[0037] S203: Control the vehicle to execute a vehicle function corresponding to the vehicle control instruction associated with the first text data.

[0038] For example, if the first text data obtained by conversion is “turn on the air conditioner”, the vehicle is controlled to execute the function of turning on the air conditioner (ie, the vehicle function corresponding to the vehicle control instruction associated with “turn on the air conditioner”).

[0039] S204: Searching a preset text database for second text data associated with second voice data inputted by each user in the next round after inputting first voice data in history, where the second text data belongs to a voice control instruction library.

[0040] For example, if the converted first text data is also "I feel so stuffy," the preset voice control command library does not contain the text data for "I feel so stuffy." Thus, the second text data associated with the second voice data input by each user after the first voice data input of "I feel so stuffy" can be searched. For example, the second text data may include, but is not limited to, text data such as "Please turn on the air conditioner," "Turn on the air conditioner," "Open the car window," "Lower the car window," "Open the sunroof," and "Open the sunroof quickly."

[0041] S205: Determine whether the amount of the second text data is greater than a set amount threshold, if not, execute S206; if yes, execute S207.

[0042] For example, the set quantity threshold may be, but is not limited to, 30, 50, or 100, etc., which is not limited here.

[0043] In addition, the method provided in an embodiment of the present application may further include: when the amount of the second text data exceeds a set amount threshold, controlling the vehicle computer to play a prompt message indicating that the vehicle computer failed to understand the user's function control intention. For example, the prompt message indicating that the vehicle computer failed to understand the user's function control intention may be, but is not limited to, "Hello, I haven't learned this skill yet."

[0044] S206: Control the vehicle computer to play a prompt message for instructing to input clearer voice data.

[0045] Understandably, the prompt information for instructing to input clearer voice data may be, “Hello, I don’t understand what you said, please speak more clearly.”

[0046] S207: Sending the standard semantic text corresponding to each type of second text data to the vehicle computer for display, wherein the semantic similarity of the second text data of the same type is greater than a set similarity threshold.

[0047] For example, "Please turn on the air conditioner" and "Turn on the air conditioner" are divided into one category; the corresponding standard semantic text is "Turn on the air conditioner"; furthermore, "Open the car window" and "Lower the car window" are divided into one category, and the corresponding standard semantic text is "Open the garage"; furthermore, "Open the sunroof" and "Open the sunroof quickly" are divided into one category, and the corresponding standard semantic text is "Open the sunroof".

[0048] For example, S207 may be specifically implemented by sorting the standard semantic texts corresponding to each type of second text data based on the number of times each type of second text data has been selected historically, with the standard semantic text corresponding to the type of second text data with the highest number of selections being ranked higher; and sending the sorted standard semantic texts to the vehicle computer for display. This makes it easier for users to select their preferred standard semantic texts.

[0049] In addition, specifically, the semantic similarity between each second text data can be determined. For example, two second text data are converted into semantic feature vectors, and the distance between the two semantic feature vectors is calculated. The distance is used to characterize the semantic similarity of the two second text data. Furthermore, a group of second text data whose semantic similarity is greater than a set semantic similarity threshold (such as 80%) can be divided into one category; the standard semantic text corresponding to each category of second text data is searched from a preset semantic database; and the standard semantic text corresponding to each category of second text data is sent to the vehicle computer display.

[0050] S208: Receive the standard semantic text selected by the user on the vehicle computer, wherein the vehicle computer controls the vehicle to execute the vehicle function according to the vehicle control instruction associated with the selected standard semantic text.

[0051] For example, if the standard semantic text selected by the user in the car computer is "turn on the air conditioner", the vehicle will execute the function of turning on the air conditioner; for another example, if the standard semantic text selected by the user in the car computer is "open the sunroof", the vehicle will execute the function of opening the sunroof.

[0052] S209: Determine whether the ratio of the number of times the selected standard semantic text is selected to the number of times all standard semantic texts are selected is greater than a set ratio threshold; if so, execute S210.

[0053] Illustratively, in some embodiments, the ratio threshold value ranges from 70% to 90%. For example, the ratio threshold value may be, but is not limited to, 70%, 80% or 90%.

[0054] S210: Establishing an association relationship between the first text data and the vehicle control instruction associated with the selected standard semantic text, and adding the association relationship to a voice control instruction library.

[0055] When the ratio of the number of times a selected standard semantic text is selected to the number of times all standard semantic texts are selected is greater than a set ratio threshold, it indicates that most users prefer the selected standard semantic text. Therefore, the first text data is associated with the vehicle control instruction associated with the selected standard semantic text and stored. For example, if the user's preferred standard semantic text is "Turn on the air conditioner," the next time the user inputs the first voice data "I feel stuffy," the vehicle will be directly controlled to execute the "Turn on the air conditioner" function. For example, if the user's preferred standard semantic text is "Open the sunroof," the next time the user inputs the first voice data "I feel stuffy," the vehicle will be directly controlled to execute the "Open the sunroof" function.

[0056] In summary, embodiments of the present application provide a method for generalizing a vehicle-mounted voice control instruction library. When it is determined that a preset voice control instruction library does not contain first text data, this indicates that the vehicle is temporarily unable to understand how to execute a vehicle function using the first text data. Furthermore, the vehicle can search a preset text database for second text data associated with second voice data entered by each user in the subsequent round following the first voice data input, where the second text data belongs to the voice control instruction library. It is understandable that since the first and second voice data are adjacent and strongly associated with the first voice data, the vehicle control instructions associated with the second text data are likely also associated with the first text data. When the amount of second text data exceeds a set threshold, the standard semantic text corresponding to each type of second text data is sent to the vehicle computer for display, where the semantic similarity of the same type of second text data exceeds a set similarity threshold. The vehicle computer receives a standard semantic text selected by the user on the vehicle computer, where the vehicle computer controls the vehicle to execute the vehicle function based on the vehicle control instructions associated with the selected standard semantic text. If the ratio of the number of times the selected standard semantic text is selected to the number of times all standard semantic texts are selected is greater than the set ratio threshold, it means that a type of second text data corresponding to the selected standard semantic text is associated with the first text data. In this way, an association relationship is established between the first text data and the vehicle control instructions associated with the selected standard semantic text, and the association relationship is added to the voice control instruction library. When the user inputs the first voice data again next time, the vehicle control instructions can be directly found based on the first text data corresponding to the first voice data, and the vehicle can be controlled to perform vehicle functions based on the vehicle control instructions. In this way, the vehicle can self-learn the number of daily texts input by the user, and based on the daily text data, the vehicle can find the corresponding vehicle control instructions, which can automatically meet the user's needs for vehicle functions, with high reliability and good user experience.

[0057] See also Figure 3 , the embodiment of the present application also provides a vehicle-mounted voice control instruction library generalization device, which is applied to a cloud server, and the cloud server is connected to the vehicle's head unit for communication. It should be noted that the basic principle and technical effects of the vehicle-mounted voice control instruction library generalization device provided in the embodiment of the present application are the same as those in the above-mentioned embodiment. For the sake of brief description, for parts not mentioned in the embodiment of the present application, please refer to the corresponding content in the above-mentioned embodiment. The device provided in the embodiment of the present application includes a data receiving unit, a data search unit, a data sending unit, and an instruction generalization unit, wherein,

[0058] The data receiving unit is used to receive first voice data sent by the user monitored by the vehicle computer and convert the first voice data into first text data.

[0059] a data search unit configured to, if it is determined that the preset voice control instruction library does not contain the first text data, search a preset text database for second text data associated with second voice data input by each user in a subsequent round after inputting the first voice data, where the second text data belongs to the voice control instruction library;

[0060] a data sending unit, configured to send the standard semantic text corresponding to each type of second text data to the vehicle computer display when the amount of the second text data is greater than a set amount threshold, wherein the semantic similarity of the second text data of the same type is greater than a set similarity threshold;

[0061] The data receiving unit is further configured to receive a standard semantic text selected by a user on the vehicle computer, wherein the vehicle computer controls the vehicle to execute a vehicle function according to a vehicle control instruction associated with the selected standard semantic text;

[0062] An instruction generalization unit is used to establish an association relationship between the first text data and the vehicle control instruction associated with the selected standard semantic text if the ratio of the number of times the selected standard semantic text is selected to the number of times all standard semantic texts are selected is greater than a set ratio threshold, and to add the association relationship to the voice control instruction library.

[0063] For example, the ratio threshold value ranges from 70% to 90%.

[0064] In some embodiments, the device provided in the present application further includes a function control unit for controlling the vehicle to execute a vehicle function corresponding to the vehicle control instruction associated with the first text data when it is determined that the preset voice control instruction library contains the first text data.

[0065] In some embodiments, the data sending unit is specifically used to sort the standard semantic texts corresponding to each type of second text data according to the number of times each type of second text data has been selected in history, and the standard semantic texts corresponding to a type of second text data with more times are ranked higher; and the sorted standard semantic texts are sent to the vehicle computer for display.

[0066] In some embodiments, the data sending unit is further specifically used to determine the semantic similarity between each second text data; classify a group of second text data whose semantic similarity is greater than a set semantic similarity threshold into a category; search for the standard semantic text corresponding to each category of second text data from a preset semantic database; and send the standard semantic text corresponding to each category of second text data to the vehicle display.

[0067] In some embodiments, the device provided in the present application further includes a prompt output unit for controlling the vehicle computer to play a prompt message for instructing input of clearer voice data when the amount of the second text data is less than or equal to a set amount threshold.

[0068] In some embodiments, the prompt output unit is further configured to control the vehicle computer to play a prompt message indicating that the user's function control intention cannot be understood when the amount of the second text data is greater than a set threshold.

[0069] In addition, an embodiment of the present application also provides a vehicle computer, including a memory, a processor, and a computer program stored in the memory and runnable on the processor. When the processor executes the computer program, the vehicle computer executes the method provided in the above embodiment of the present application.

[0070] In addition, an embodiment of the present application further provides a storage medium, which stores a computer program. When the computer program is executed by a processor, the computer executes the method provided in the above embodiment of the present application.

[0071] In addition, an embodiment of the present application also provides a computer program product, including a computer program. When the computer program is run, the vehicle computer executes the method provided in the above embodiment of the present application.

[0072] While the above description does not provide detailed technical details regarding the patterning of each layer, those skilled in the art will appreciate that various technical means can be employed to form layers, regions, and the like in desired shapes. Furthermore, those skilled in the art may devise methods that differ from those described above to achieve the same structure. Furthermore, while each embodiment has been described separately, this does not mean that the measures in each embodiment cannot be advantageously combined.

[0073] Although the preferred embodiments of the present application have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present application.

[0074] Obviously, those skilled in the art may make various changes and modifications to this application without departing from the spirit and scope of this application. Thus, if these modifications and variations of this application fall within the scope of the claims of this application and their equivalents, this application is intended to include these modifications and variations.

Claims

1. A method for generalizing a vehicle-mounted voice control instruction library, characterized in that: Applied to a cloud server, the cloud server being communicatively connected to a vehicle computer, the method comprising: receiving first voice data sent by a user monitored by the vehicle computer, and converting the first voice data into first text data; If it is determined that the preset voice control instruction library does not include the first text data, searching a preset text database for second text data associated with second voice data input by each user in a subsequent round after inputting the first voice data, where the second text data belongs to the voice control instruction library; When the amount of the second text data is greater than a set amount threshold, the standard semantic text corresponding to each type of the second text data is sent to the vehicle computer for display, wherein the semantic similarity of the second text data of the same type is greater than a set similarity threshold; receiving a standard semantic text selected by a user on the vehicle computer, wherein the vehicle computer controls the vehicle to perform a vehicle function according to a vehicle control instruction associated with the selected standard semantic text; If the ratio of the number of times the selected standard semantic text is selected to the number of times all standard semantic texts are selected is greater than a set ratio threshold, an association relationship is established between the first text data and the vehicle control instruction associated with the selected standard semantic text, and the association relationship is added to the voice control instruction library.

2. The method according to claim 1, characterized in that After converting the first voice data into first text data, the method further includes: When it is determined that the preset voice control instruction library contains the first text data, the vehicle is controlled to execute a vehicle function corresponding to the vehicle control instruction associated with the first text data.

3. The method according to claim 1, characterized in that The sending of the standard semantic text corresponding to each type of the second text data to the vehicle computer display includes: sorting the standard semantic texts corresponding to each category of the second text data according to the number of times each category of the second text data has been selected in the past, wherein the standard semantic text corresponding to a category of the second text data having a greater number of selections is ranked higher; The sorted standard semantic text is sent to the vehicle computer for display.

4. The method according to claim 1, wherein The sending of the standard semantic text corresponding to each type of the second text data to the vehicle computer display includes: Determining semantic similarity between each of the second text data; Classifying a group of second text data whose semantic similarities are greater than a set semantic similarity threshold into one category; Searching a preset semantic database for a standard semantic text corresponding to each type of the second text data; The standard semantic text corresponding to each type of the second text data is sent to the vehicle computer for display.

5. The method according to claim 1, wherein The method further includes: when the amount of the second text data is less than or equal to a set amount threshold, controlling the vehicle computer to play prompt information for instructing to input clearer voice data.

6. The method according to claim 1, characterized in that The method further includes: when the amount of the second text data is greater than a set amount threshold, controlling the vehicle computer to play a prompt message indicating that the vehicle computer fails to understand the user's function control intention.

7. The method according to any one of claims 1 to 6, characterized in that: The ratio threshold value ranges from 70% to 90%.

8. A vehicle computer, 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 the computer program, the vehicle computer executes the method according to any one of claims 1 to 7.

9. A storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the computer is caused to perform the method according to any one of claims 1 to 7.

10. A computer program product comprising a computer program, characterized in that When the computer program is executed, the vehicle computer executes the method as claimed in any one of claims 1 to 7.

Images