Voice information processing method and system, electronic equipment and vehicle

Abstract

The invention discloses a voice information processing method and system, electronic equipment and a vehicle. First voice information is obtained; determining at least one piece of associated information corresponding to the first voice information based on the recognition of the first voice information; obtaining second voice information, wherein the second voice information is supplementary voice information of the first voice information; determining target information matched with the second voice information from the at least one piece of associated information based on recognition of the second voice information; and outputting the target information. According to the scheme, after the first voice information is obtained, the at least one piece of associated information can be determined based on the first voice information, then the second voice information for supplementing the first voice information is obtained, and the actually required target information can be determined from the at least one piece of associated information based on the second voice information; the required target information can be accurately determined through two times of voice input, and the processing efficiency and the user experience are improved.

Description

Technical Field

[0001] The present application relates to the field of information processing, and in particular to a voice information processing method, system, electronic equipment and vehicle. Background Art

[0002] Currently, when information is searched through voice input, a large number of search results are usually output, but information that completely matches the voice input cannot be accurately output. Summary of the invention

[0003] In view of this, the present application provides a voice information processing method, system, electronic device and vehicle, and the specific solutions are as follows:

[0004] A method for processing speech information, comprising:

[0005] obtaining a first voice message;

[0006] Determine at least one associated information corresponding to the first voice information based on the recognition of the first voice information;

[0007] Obtaining second voice information, where the second voice information is supplementary voice information of the first voice information;

[0008] determining target information matching the second voice information from the at least one associated information based on the recognition of the second voice information;

[0009] The target information is output.

[0010] Further, the determining at least one associated information corresponding to the first voice information based on the recognition of the first voice information includes:

[0011] Recognizing the first voice information to obtain text information;

[0012] At least one associated information corresponding to the text information is determined.

[0013] Further, the determining of at least one associated information corresponding to the text information includes:

[0014] Searching for a pre-stored information record to determine whether there is a record file including the text information in the subject content in the information record, wherein the information record includes a plurality of record files;

[0015] If it is determined that a record file including the text information in the subject content exists in the information record, the record file including the text information in the subject content is determined as associated information corresponding to the text information.

[0016] Further, the determining of at least one associated information corresponding to the text information includes:

[0017] The determination information includes at least one associated information of the text information.

[0018] Further, the determining target information matching the second voice information from the at least one associated information based on the recognition of the second voice information includes:

[0019] Determining supplementary content to supplement the first voice information by recognizing the second voice information;

[0020] Determine relevant content of each associated information in the at least one associated information, wherein the relevant content is content other than the associated information itself;

[0021] Obtaining a comparison result obtained by comparing the relevant content of each associated information with the supplementary content;

[0022] If it is determined based on the comparison result that the relevant content of the first associated information in the at least one associated information matches the supplementary content, then the first associated information is determined to be the target information matching the second voice information.

[0023] Furthermore, the relevant contents of the associated information at least include:

[0024] Information corresponding to the keywords in the subject content of the associated information;

[0025] or,

[0026] The information record used to store at least one associated information stores information corresponding to the associated information.

[0027] Further, the determining target information matching the second voice information from the at least one associated information based on the recognition of the second voice information includes:

[0028] Determining supplementary content to supplement the first voice information by recognizing the second voice information;

[0029] Determining whether the subject content of each associated information in the at least one associated information includes the supplementary content;

[0030] If it is determined that the subject content of the second associated information in the at least one associated information includes the supplementary content, the second associated information is determined as target information matching the second voice information.

[0031] A voice information processing system, comprising:

[0032] A first obtaining unit, used to obtain first voice information;

[0033] A first determining unit, configured to determine at least one associated information corresponding to the first voice information based on the recognition of the first voice information;

[0034] A second obtaining unit, configured to obtain second voice information, where the second voice information is supplementary voice information to the first voice information;

[0035] A second determining unit, configured to determine target information matching the second voice information from the at least one associated information based on the recognition of the second voice information;

[0036] An output unit is used to output the target information.

[0037] An electronic device, comprising:

[0038] A sound receiving device, used to obtain first voice information and second voice information, wherein the second voice information is supplementary voice information of the first voice information;

[0039] A processor is used to determine at least one associated information corresponding to the first voice information based on the recognition of the first voice information; after obtaining the second voice information, determine the target information matching the second voice information from the at least one associated information based on the recognition of the second voice information; and output the target information.

[0040] A vehicle comprising:

[0041] A control device, wherein the control device is used to execute the voice information processing method as described in any one of the above.

[0042] It can be seen from the above technical scheme that the voice information processing method, system, electronic device and vehicle disclosed in the present application obtain first voice information; determine at least one related information corresponding to the first voice information based on the recognition of the first voice information; obtain second voice information, which is supplementary voice information for the first voice information; determine target information matching the second voice information from at least one related information based on the recognition of the second voice information; and output the target information. After obtaining the first voice information, this scheme can determine at least one related information based on the first voice information, and then obtain the second voice information used to supplement the first voice information, and can determine the actually required target information from at least one related information based on the second voice information, thereby realizing that the required target information can be accurately determined through two voice inputs, thereby improving processing efficiency and user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0044] Figure 1 A flowchart of a voice information processing method disclosed in an embodiment of the present application;

[0045] Figure 2 A flowchart of a voice information processing method disclosed in an embodiment of the present application;

[0046] Figure 3 A flowchart of a voice information processing method disclosed in an embodiment of the present application;

[0047] Figure 4 A schematic diagram of the structure of a voice information processing system disclosed in an embodiment of the present application;

[0048] Figure 5 A schematic diagram of the structure of an electronic device disclosed in an embodiment of the present application. DETAILED DESCRIPTION

[0049] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0050] The present application discloses a method for processing speech information, and its flow chart is as follows: Figure 1 As shown, including:

[0051] Step S11, obtaining first voice information;

[0052] Step S12: determining at least one associated information corresponding to the first voice information based on the recognition of the first voice information;

[0053] Step S13, obtaining second voice information, where the second voice information is supplementary voice information of the first voice information;

[0054] Step S14, determining target information matching the second voice information from at least one associated information based on the recognition of the second voice information;

[0055] Step S15: Output target information.

[0056] When searching for information by voice, usually after the voice is obtained, the voice is recognized and the content to be searched is determined based on the recognition result.

[0057] Regardless of the language, there are usually homophones but different characters. This leads to the situation that when searching for information based on voice, if the voice recognition is wrong, the search content may be inaccurate; or, there is no problem with the voice recognition, but multiple recognition results are obtained through voice recognition, and it is impossible to accurately determine the content that the user actually needs.

[0058] Based on this, in this solution, the first voice information is first obtained, a range is determined by recognizing the first voice information, and then the second voice information is obtained. The content actually required by the user is determined from the previously determined range by recognizing the second voice information, thereby improving the accuracy of voice recognition and avoiding the situation where multiple recognition results cannot accurately determine the content to be searched. At the same time, it also avoids the situation where the search content is inaccurate due to voice recognition errors.

[0059] Specifically, a first voice message is obtained. The first voice message is first input by a user into a voice information processing system for executing a voice information processing method. Voice recognition is performed on the first voice message to determine a preliminary determination result of the system for the user's needs. The preliminary determination result may be multiple, that is, voice recognition is performed on the first voice message to determine at least one associated information corresponding to the first voice message.

[0060] Among them, at least one associated information determined based on the recognition of the first voice information can be: the first recognition information obtained by recognizing the first voice information, directly determining the first recognition information as the associated information, such as: the user outputs the first voice information, and the system recognizes the first voice information and obtains the first recognition information as "driving", then "driving" can be directly used as the associated information; in addition, due to the difference in pronunciation when the user outputs the voice, the system may recognize "driving", or it may be "trip", "formation", etc., then the associated information determined by the system may also be "driving", "trip" and "formation".

[0061] In addition, at least one associated information determined based on the recognition of the first voice information can also be: the first voice information is recognized to obtain the first recognition information, and the associated information is obtained based on the first recognition information, that is, the associated information is information that has an associated relationship with the first recognition information, such as: the user outputs the first voice information, and the system recognizes the first voice information and obtains the first recognition information as "driving", and the determined associated information can be "automatic locking while driving", "daytime running lights", "driving area lighting", etc.

[0062] After determining at least one associated information based on the first voice information, second voice information output by the user is obtained, the second voice information is supplementary voice information used to supplement the first voice information, and the second voice information is recognized so as to determine the final target information from at least one associated information and output it.

[0063] The target information is obtained based on the first voice information and the second voice information, and belongs to one of the at least one related information.

[0064] The second voice information supplements the first voice information. After the first voice information is identified and at least one associated information is obtained, the second voice information is used to select one piece of information from the at least one associated information as the target information. For example, based on the identification of the first voice information, a list of associated information is obtained, and the list of associated information includes: 1 Automatic locking while driving, 2 Daytime running lights, 3 Driving zone lighting, then the second voice information can be "the first one", after the second voice information is identified, its supplementary content is determined, and then the first one is selected from the list of associated information as the target information based on the content, that is, "1 Automatic locking while driving"; or, if the second voice information is "Automatic locking while driving", then the target information can be determined as "1 Automatic locking while driving".

[0065] After determining the target information, the target information is output, or the content specified by the target information is output, such as: a video related to "automatic locking while driving" or an audio introduction to the content of "automatic locking while driving", so that the user can obtain the information he needs.

[0066] The voice information processing method disclosed in this embodiment obtains first voice information; determines at least one associated information corresponding to the first voice information based on the recognition of the first voice information; obtains second voice information, which is supplementary voice information for the first voice information; determines target information matching the second voice information from at least one associated information based on the recognition of the second voice information; and outputs the target information. After obtaining the first voice information, this solution can determine at least one associated information based on the first voice information, and then obtain the second voice information used to supplement the first voice information, and can determine the actually required target information from at least one associated information based on the second voice information, thereby achieving the ability to accurately determine the required target information through two voice inputs, thereby improving processing efficiency and user experience.

[0067] This embodiment discloses a method for processing voice information, and its flow chart is as follows: Figure 2 As shown, including:

[0068] Step S21, obtaining first voice information;

[0069] Step S22: Recognize the first voice information to obtain text information; determine at least one associated information corresponding to the text information;

[0070] Step S23, obtaining second voice information, where the second voice information is supplementary voice information of the first voice information;

[0071] Step S24, determining target information matching the second voice information from at least one associated information based on the recognition of the second voice information;

[0072] Step S25: output target information.

[0073] The first voice information is recognized to obtain text information corresponding to the first voice information.

[0074] Text information refers to specific text content. When voice information is converted into text content, due to the situation of homophones but different characters, the text content converted from the same voice information may be different. Therefore, multiple text information may be obtained by recognizing the first voice information. Multiple pieces of associated information may also correspond to each piece of text information. Therefore, multiple pieces of associated information may also be obtained based on the first voice information.

[0075] For example: the first voice information and the second voice information are in Chinese, then when the first voice information is "bei yuan", voice recognition is performed on it, and the obtained text information at least includes: "Beiyuan", "Beiyuan", "Beiyuan", etc., and each text information may have corresponding related information, such as: the related information corresponding to "Beiyuan" at least includes: "Beiyuan Home", "Beiyuan East District", etc., and the related information corresponding to "Beiyuan" at least includes: "XX Hospital Beiyuan", etc., and the related information corresponding to "Beiyuan" at least includes: "XX Park Beiyuan", etc.

[0076] When the first voice information is "beiyuan", voice recognition is performed on it, multiple text information is obtained, and multiple related information corresponding to the text information is determined. After multiple related information is obtained, the second voice information is obtained, and the target information actually required is determined from the multiple related information based on the recognition of the second voice information.

[0077] Continuing with the above example, when the first voice information is "beiyuan", multiple related information is determined, and the second voice information is obtained and recognized. If the second voice information is determined to be "hospital", or the keyword information in the second voice information is "hospital", then based on the recognized second voice information and / or the keyword information "hospital" in the second voice information, the target information can be determined from multiple related information, and the target information is "XX Hospital North Branch". Therefore, when the target information is output, the output is the introduction, address information, or navigation information of "XX Hospital North Branch".

[0078] Then, at least one associated information corresponding to the text information is determined, which can be: determining that the information includes at least one associated information of the text information, that is, searching the network for at least one associated information corresponding to the text information, such as searching for an address through an online map, which is to search the network for an address corresponding to a certain text information.

[0079] For example, the first voice information "beiyuan" is input into the online map application, and voice recognition is first performed on it to obtain text information, such as: "Beiyuan", "Beiyuan", "Beiyuan", etc., and then corresponding related information is obtained based on the text information, such as: "Beiyuan Home", "Beiyuan East District", "XX Hospital North Hospital", "XX Park North Park", etc., and then the second voice information "yiyuan" is input into the online map application, and voice recognition is performed on it to obtain the information "hospital", thereby determining the target information "XX Hospital North Hospital" related to the second voice information from the related information, and then outputting the target information, that is, outputting the navigation information to the "XX Hospital North Hospital".

[0080] In addition, determining at least one associated information corresponding to the text information may also include: searching a pre-stored information record to determine whether there is a record file in the information record that includes text information in the subject content, wherein the information record includes multiple record files; if it is determined that there is a record file in the information record that includes text information in the subject content, then determining the record file in the subject content that includes text information as the associated information corresponding to the text information.

[0081] That is, related content is searched through locally stored information records to determine associated information.

[0082] An information record including a plurality of record files is stored locally, and relevant information can be queried from the information record by voice input.

[0083] For example: the information record is the vehicle's instruction manual. When you need to query relevant information about the use of the vehicle, you can input the first voice information, such as: the first voice information is "tai ya", and the text information obtained by voice recognition is "tire pressure". Find out whether the subject content of each description part in the vehicle's instruction manual includes the subject content of "tire pressure". If so, the description parts corresponding to these subject contents are determined as related information. For example: the vehicle's instruction manual includes the following parts, and its subject content includes "tire pressure": "What's the matter if the tire pressure monitoring does not display", "How to deal with low tire pressure", "What is the reason why the tire pressure monitoring system warning light is on", "How to turn on tire pressure monitoring", etc., and then obtain the second voice information. If the second voice information is "kaiqi", it is recognized as "turn on", and the subject content of "how to turn on tire pressure monitoring" is determined from the related information, and the specific description content in the vehicle's instruction manual corresponding to this subject content is output. At this time, it can be output in the form of voice or in the form of video demonstration.

[0084] The voice information processing method disclosed in this embodiment obtains first voice information; recognizes the first voice information to obtain text information, and determines at least one associated information corresponding to the text information; obtains second voice information, which is supplementary voice information for the first voice information; determines target information matching the second voice information from at least one associated information based on the recognition of the second voice information; and outputs the target information. After obtaining the first voice information, this solution can determine at least one associated information based on the first voice information, and then obtains the second voice information used to supplement the first voice information. Based on the second voice information, it can determine the actually required target information from at least one associated information, thereby achieving the goal of accurately determining the required target information through two voice inputs, thereby improving processing efficiency and user experience.

[0085] This embodiment discloses a method for processing voice information, and its flow chart is as follows: Figure 3 As shown, including:

[0086] Step S31, obtaining first voice information;

[0087] Step S32: determining at least one associated information corresponding to the first voice information based on the recognition of the first voice information;

[0088] Step S33, obtaining second voice information, where the second voice information is supplementary voice information of the first voice information;

[0089] Step S34, determining supplementary content to supplement the first voice information by identifying the second voice information;

[0090] Step S35, determining relevant content of each associated information in at least one associated information, wherein the relevant content is the content of the non-associated information itself; obtaining a comparison result obtained by comparing the relevant content of each associated information with the supplementary content;

[0091] Step S36: determining, based on the comparison result, that the relevant content of the first associated information in the at least one associated information matches the supplementary content, and determining that the first associated information is the target information that matches the second voice information;

[0092] Step S37: output target information.

[0093] After obtaining at least one associated information corresponding to the first voice information through recognition of the first voice information, the second voice information is obtained. Since the second voice information is supplementary information of the first voice information, the supplementary content that supplements the first voice information can be determined by recognizing the second voice information.

[0094] Since the target information required by the user cannot be clearly determined through the first voice information, after obtaining at least one associated information through the first voice information, the target information is clarified from the at least one associated information by supplementing the first voice information.

[0095] The supplementary content that supplements the first voice information is determined by identifying the second voice information, that is, the second voice information is identified to obtain the specific content of the second voice information, and the specific content is the supplementary content that supplements the first voice information.

[0096] The relevant content of each related information is the content that is related to the related information and is not the content of the related information itself, such as: content that has a causal relationship with the related information, or content that has a progressive relationship with the related information, or content that has a conditional relationship with the related information, or content that has a succession relationship with the related information, or content that has a parallel relationship with the related information, or content that has a directional relationship with the related information, etc.

[0097] For example: the first voice information is "XX Community". After voice recognition, the associated information obtained includes at least: "XX Community East Gate", "XX Community South Gate", "XX Community North Gate", etc. At this time, the second voice information is obtained. If the second voice information is "next to the gas station", the relevant content of each associated information is determined. If it is determined that "XX Community South Gate" is next to the gas station, at this time, it is determined that the relevant content of "XX Community South Gate" matches "next to the gas station". At this time, the final target information can be determined as "XX Community South Gate".

[0098] Alternatively, the relevant content of the associated information may also be: information corresponding to a keyword in the subject content of the associated information.

[0099] The subject content of the associated information includes multiple information, which may include one or multiple keyword information. The supplementary content may be related to the extended information of one or multiple keyword information in the subject content of the associated information.

[0100] For example, if the keyword included in the subject content of the associated information is "light", then the related content of the associated information may be "position light", "high beam light", "fog light" and other information.

[0101] In addition, the related content of the associated information may also be: information stored corresponding to the associated information in an information record for storing at least one associated information.

[0102] The information record is pre-stored information, including multiple record files, and the associated information is actually the record file determined from the information record. The information stored in the information record corresponding to the associated information, that is, as long as the information record contains information related to the associated information, it can be confirmed as the relevant content of the associated information.

[0103] For example, if the information record is a vehicle manual and the associated information is "indicator light is on", then a complete chapter corresponding to the content "indicator light is on" appears in the specific content of the vehicle manual, which can be confirmed as the relevant content of the associated information.

[0104] In addition, determining the target information matching the second voice information from at least one associated information based on the recognition of the second voice information may also be:

[0105] Determine the supplementary content that supplements the first voice information by identifying the second voice information; determine whether the subject content of each related information in at least one related information includes the supplementary content; if it is determined that the subject content of the second related information in at least one related information includes the supplementary content, determine the second related information as the target information that matches the second voice information.

[0106] That is, when the second voice information is used as the supplementary content of the first voice information, it can be directly determined based on the subject content of the associated information whether the supplementary content is included, thereby determining the target information. If the subject content of the associated information includes the supplementary content identified by the second voice information, the associated information is determined as the target information; if the subject content of the associated information does not include the supplementary content identified by the second voice information, the associated information is not output as the target information.

[0107] For example: the first voice information is "high beam", and the related information obtained based on the first voice information can be: "How to turn on the high beam", "How to turn off the high beam", "Where is the high beam switch", etc. The second voice information is the supplementary content of the first voice information. If the second voice information is "switch", the subject content of the related information "Where is the high beam switch" includes the second voice information "switch". In this case, the related information "Where is the high beam switch" can be directly determined as the target information, and the specific content of "Where is the high beam switch" can be output, that is, the location display or voice prompt of the high beam switch.

[0108] The voice information processing method disclosed in this embodiment obtains first voice information; determines at least one associated information corresponding to the first voice information based on the recognition of the first voice information; obtains second voice information, which is the supplementary voice information of the first voice information; determines the supplementary content that supplements the first voice information by recognizing the second voice information, determines the relevant content of each associated information in at least one associated information, and the relevant content is the content of the non-associated information itself; obtains the comparison result obtained by comparing the relevant content of each associated information with the supplementary content, determines based on the comparison result that the relevant content of the first associated information in at least one associated information matches the supplementary content, and determines that the first associated information is the target information that matches the second voice information; and outputs the target information. After obtaining the first voice information, this scheme can determine at least one associated information based on the first voice information, and then obtains the second voice information used to supplement the first voice information, and can determine the actually required target information from at least one associated information based on the second voice information, so that the required target information can be accurately determined through two voice inputs, thereby improving processing efficiency and user experience.

[0109] This embodiment discloses a voice information processing system, and its structural diagram is shown in FIG. Figure 4 As shown, including:

[0110] A first obtaining unit 41 , a first determining unit 42 , a second obtaining unit 43 , a second determining unit 44 and an output unit 45 .

[0111] The first obtaining unit 41 is used to obtain the first voice information;

[0112] The first determining unit 42 is used to determine at least one associated information corresponding to the first voice information based on the recognition of the first voice information;

[0113] The second obtaining unit 43 is used to obtain second voice information, where the second voice information is supplementary voice information of the first voice information;

[0114] The second determining unit 44 is used to determine the target information matching the second voice information from at least one associated information based on the recognition of the second voice information;

[0115] The output unit 45 is used to output target information.

[0116] Further, the first determining unit is used for:

[0117] The first voice information is recognized to obtain text information; and at least one associated information corresponding to the text information is determined.

[0118] Further, the first determining unit is used for:

[0119] Search for pre-stored information records to determine whether there is a record file including text information in the subject content in the information record, wherein the information record includes multiple record files; if it is determined that there is a record file including text information in the subject content in the information record, determine the record file including text information in the subject content as associated information corresponding to the text information.

[0120] Further, the first determining unit is used for:

[0121] The information is determined to include at least one associated information of the text information.

[0122] Further, the second determining unit is used for:

[0123] The method comprises the following steps: determining the supplementary content that supplements the first voice information by identifying the second voice information; determining the relevant content of each related information in at least one related information, wherein the relevant content is the content of the non-related information itself; obtaining a comparison result by comparing the relevant content of each related information with the supplementary content; determining based on the comparison result that the relevant content of the first related information in at least one related information matches the supplementary content, and then determining that the first related information is the target information that matches the second voice information.

[0124] Furthermore, the relevant contents of the associated information at least include:

[0125] Information corresponding to a keyword in the subject content of the associated information; or information stored corresponding to the associated information in an information record for storing at least one associated information.

[0126] Further, the second determining unit is used for:

[0127] Determine the supplementary content that supplements the first voice information by identifying the second voice information; determine whether the subject content of each related information in at least one related information includes the supplementary content; if it is determined that the subject content of the second related information in at least one related information includes the supplementary content, determine the second related information as the target information that matches the second voice information.

[0128] The voice information processing system disclosed in this embodiment is implemented based on the voice information processing method disclosed in the above embodiment, which will not be described in detail here.

[0129] The voice information processing system disclosed in this embodiment obtains first voice information; determines at least one associated information corresponding to the first voice information based on the recognition of the first voice information; obtains second voice information, which is supplementary voice information for the first voice information; determines target information matching the second voice information from at least one associated information based on the recognition of the second voice information; and outputs the target information. After obtaining the first voice information, this solution can determine at least one associated information based on the first voice information, and then obtain the second voice information used to supplement the first voice information, and can determine the actually required target information from at least one associated information based on the second voice information, thereby achieving the goal of accurately determining the required target information through two voice inputs, thereby improving processing efficiency and user experience.

[0130] This embodiment discloses an electronic device, and its structural diagram is as follows: Figure 5 As shown, including:

[0131] The sound receiving device 51 and the processor 52 .

[0132] The sound receiving device 51 is used to obtain the first voice information and the second voice information, and the second voice information is the supplementary voice information of the first voice information;

[0133] The processor 52 is used to determine at least one associated information corresponding to the first voice information based on the recognition of the first voice information; after obtaining the second voice information, determine the target information matching the second voice information from the at least one associated information based on the recognition of the second voice information; and output the target information.

[0134] The electronic device disclosed in this embodiment is implemented based on the voice information processing method disclosed in the above embodiment, which will not be described in detail here.

[0135] The electronic device disclosed in this embodiment obtains first voice information; determines at least one associated information corresponding to the first voice information based on the recognition of the first voice information; obtains second voice information, which is supplementary voice information for the first voice information; determines target information matching the second voice information from at least one associated information based on the recognition of the second voice information; and outputs the target information. After obtaining the first voice information, this solution can determine at least one associated information based on the first voice information, and then obtain the second voice information for supplementing the first voice information, and can determine the actually required target information from at least one associated information based on the second voice information, thereby achieving the ability to accurately determine the required target information through two voice inputs, thereby improving processing efficiency and user experience.

[0136] This embodiment discloses a vehicle, which includes a control device, and the control device is used to execute the above-mentioned voice information processing method.

[0137] The embodiment of the present application also provides a readable storage medium on which a computer program is stored. The computer program is loaded and executed by a processor to implement the steps of the above-mentioned voice information processing method. The specific implementation process can refer to the description of the corresponding part of the above-mentioned embodiment, which will not be repeated in this embodiment.

[0138] The present application also proposes a computer program product or a computer program, which includes a computer instruction stored in a computer-readable storage medium. The processor of the electronic device reads the computer instruction from the computer-readable storage medium, and the processor executes the computer instruction, so that the electronic device executes the method provided in various optional implementations of the above-mentioned voice information processing method or voice information processing system. The specific implementation process can refer to the description of the above-mentioned corresponding embodiment, and will not be repeated.

[0139] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.

[0140] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0141] The steps of the method or algorithm described in conjunction with the embodiments disclosed herein may be implemented directly using hardware, a software module executed by a processor, or a combination of the two. The software module may be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0142] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for processing speech information, characterized in that: include: obtaining a first voice message; Determine at least one associated information corresponding to the first voice information based on the recognition of the first voice information; Obtaining second voice information, where the second voice information is supplementary voice information of the first voice information; determining target information matching the second voice information from the at least one associated information based on the recognition of the second voice information; The target information is output.

2. The method according to claim 1, characterized in that The determining at least one associated information corresponding to the first voice information based on the recognition of the first voice information includes: Recognizing the first voice information to obtain text information; At least one associated information corresponding to the text information is determined.

3. The method according to claim 2, characterized in that The determining of at least one associated information corresponding to the text information includes: Searching for a pre-stored information record to determine whether there is a record file including the text information in the subject content in the information record, wherein the information record includes a plurality of record files; If it is determined that a record file including the text information in the subject content exists in the information record, the record file including the text information in the subject content is determined as associated information corresponding to the text information.

4. The method according to claim 2, characterized in that: The determining of at least one associated information corresponding to the text information includes: The determination information includes at least one associated information of the text information.

5. The method according to claim 1, characterized in that The determining, based on the recognition of the second voice information, target information matching the second voice information from the at least one associated information comprises: Determining supplementary content to supplement the first voice information by recognizing the second voice information; Determine relevant content of each associated information in the at least one associated information, wherein the relevant content is content other than the associated information itself; Obtaining a comparison result obtained by comparing the relevant content of each associated information with the supplementary content; If it is determined based on the comparison result that the relevant content of the first associated information in the at least one associated information matches the supplementary content, then the first associated information is determined to be the target information matching the second voice information.

6. The method according to claim 5, characterized in that The relevant contents of the associated information at least include: Information corresponding to the keywords in the subject content of the associated information; or, The information record used to store at least one associated information stores information corresponding to the associated information.

7. The method according to claim 1, characterized in that The determining, based on the recognition of the second voice information, target information matching the second voice information from the at least one associated information comprises: Determining supplementary content to supplement the first voice information by recognizing the second voice information; Determining whether the subject content of each associated information in the at least one associated information includes the supplementary content; If it is determined that the subject content of the second associated information in the at least one associated information includes the supplementary content, the second associated information is determined as target information matching the second voice information.

8. A voice information processing system, characterized in that: include: A first obtaining unit, used to obtain first voice information; A first determining unit, configured to determine at least one associated information corresponding to the first voice information based on the recognition of the first voice information; A second obtaining unit, configured to obtain second voice information, where the second voice information is supplementary voice information to the first voice information; A second determining unit, configured to determine target information matching the second voice information from the at least one associated information based on the recognition of the second voice information; An output unit is used to output the target information.

9. An electronic device, characterized in that: include: A sound receiving device, used to obtain first voice information and second voice information, wherein the second voice information is supplementary voice information of the first voice information; a processor, configured to determine at least one associated information corresponding to the first voice information based on the recognition of the first voice information; After obtaining the second voice information, target information matching the second voice information is determined from the at least one associated information based on the recognition of the second voice information; and the target information is output.

10. A vehicle, characterized in that: include: A control device, wherein the control device is used to execute the speech information processing method as described in any one of claims 1-7.

Images