Target data query method, apparatus, readable storage medium and electronic device

Abstract

This invention provides a method, apparatus, computer-readable storage medium, and electronic device for querying target data. The method includes: acquiring a user's voice command; determining a target voiceprint account based on the voice command and a stored voiceprint account; and determining target query data based on the voice command and stored data information in the target voiceprint account. The technical solution provided by this invention utilizes the uniqueness of voiceprints, opening different voiceprint accounts for different voiceprints. When a user needs to query data, they only need to issue a voice command to quickly and accurately retrieve the target query data, resulting in high query efficiency and improving the reuse rate of stored data information in the target voiceprint account.

Description

Technical Field

[0001] This invention relates to the field of data query technology, and more specifically, to a method, apparatus, readable storage medium, and electronic device for querying target data. Background Technology

[0002] People often rate places they've visited, such as restaurants and tourist destinations. Currently, users who want to find their rated places generally need to open a specific application, search through historical review records, and then find the review they need from a large number of records. As the number of historical reviews increases, it often takes a long time for users to find the review they want. Some users also use Notepad to record review data. However, Notepad data is unstructured, and Notepad's search capabilities are weak, so users also need to spend a considerable amount of time finding the review they want. Therefore, the existing review data has poor reusability, and the methods for querying review data are inefficient. Summary of the Invention

[0003] This invention provides a target data query method, apparatus, computer-readable storage medium, and electronic device to solve the technical problem of low efficiency in existing data query methods.

[0004] Firstly, a method for querying target data is provided, which specifically includes the following steps:

[0005] Obtain the user's voice commands;

[0006] Based on the voice command and the stored voiceprint account, determine the target voiceprint account;

[0007] Based on the voice command and the stored data information in the target voiceprint account, the target query data is determined.

[0008] Secondly, a target data query device is provided, specifically including the following modules:

[0009] The command acquisition module is used to acquire the user's voice commands;

[0010] The account determination module is used to determine the target voiceprint account based on the voice command and the stored voiceprint account;

[0011] The data query module is used to determine the target query data based on the voice command and the stored data information in the target voiceprint account.

[0012] Thirdly, a computer-readable storage medium is provided, the storage medium storing a computer program for executing the above-described target data query method.

[0013] Fourthly, an electronic device is provided, the electronic device comprising:

[0014] processor;

[0015] Memory used to store the processor's executable instructions;

[0016] The processor is configured to read the executable instructions from the memory and execute the instructions to implement the target data query method described above.

[0017] Compared with the prior art, the target data query method, apparatus, computer-readable storage medium, and electronic device provided by the present invention have at least the following beneficial effects:

[0018] The technical solution provided by this invention first acquires the user's voice command, and then determines the target voiceprint account based on the acquired voice command and the stored voiceprint account. The target voiceprint account is the selected voiceprint account to be accessed, and it stores stored data information, which may include the user's historical evaluation data. Therefore, after determining the target voiceprint account, the target query data can be determined based on the voice command and the stored data information in the target voiceprint account. This technical solution utilizes the uniqueness of voiceprints to open different voiceprint accounts for different voiceprints. When a user needs to query data, they only need to issue a voice command to quickly and accurately retrieve the target query data, resulting in high query efficiency and improved reuse rate of the stored data information in the target voiceprint account. Attached Figure Description

[0019] To more clearly illustrate the technical solution of the present invention, the accompanying drawings used in the description of the present invention will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 This is a flowchart illustrating a target data query method provided by an exemplary embodiment of the present invention. Figure 1 ;

[0021] Figure 2 This is a flowchart illustrating a target data query method provided by an exemplary embodiment of the present invention. Figure 2 ;

[0022] Figure 3 This is a flowchart illustrating a target data query method provided by an exemplary embodiment of the present invention. Figure 3 ;

[0023] Figure 4This is a flowchart illustrating a target data query method provided by an exemplary embodiment of the present invention. Figure 4 ;

[0024] Figure 5 This is a flowchart illustrating a target data query method provided by an exemplary embodiment of the present invention. Figure 5 ;

[0025] Figure 6 This is a flowchart illustrating a target data query method provided by an exemplary embodiment of the present invention. Figure 6 ;

[0026] Figure 7 This is a flowchart illustrating a target data query method provided by an exemplary embodiment of the present invention. Figure 7 ;

[0027] Figure 8 This is a schematic diagram of the structure of a target data query device provided in an exemplary embodiment of the present invention;

[0028] Figure 9 This is a structural diagram of an electronic device provided in an exemplary embodiment of the present invention. Detailed Implementation

[0029] The technical solutions of this invention will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of the embodiments of this invention.

[0030] People often rate places they've visited, such as restaurants and tourist destinations. Currently, users who want to find their rated places generally need to open a specific application, search through historical rating records, and find the desired rating from a large number of records. As the number of historical rating records increases, it often takes a long time for users to find the desired rating. Some users also use Notepad to record rating data. Notepad-recorded rating data is unstructured, and Notepad's search capabilities are weak, so users also need to spend a considerable amount of time finding the desired rating. Therefore, existing rating data has poor reusability, and the rating data query methods are inefficient. To solve the technical problem of low efficiency in existing data query methods, this invention provides the following exemplary methods, apparatus, electronic devices, computer program products, and computer-readable storage media.

[0031] Exemplary methods

[0032] Figure 1This is a flowchart illustrating a target data query method provided in an exemplary embodiment of the present invention, which specifically includes the following steps:

[0033] Step 10: Obtain the user's voice commands.

[0034] In one embodiment, a voice command refers to the collected user voice information. Specifically, a voice acquisition device is used to collect the user's voice commands, which includes, but is not limited to, mobile phones, tablets, headphones, and in-vehicle smart terminals. For example, when a user issues a voice command in a vehicle, the in-vehicle smart terminal collects the user's voice command and uploads it to the cloud, allowing the cloud to access the user's voice command.

[0035] Step 20: Determine the target voiceprint account based on the voice command and the stored voiceprint account.

[0036] In one embodiment, storing a voiceprint account refers to a pre-established and stored voiceprint account, with different voiceprints corresponding to different voiceprint accounts. The target voiceprint account is the voiceprint account that will be accessed based on a voice command.

[0037] Step 30: Determine the target query data based on the voice command and the stored data information in the target voiceprint account.

[0038] In one embodiment, the target voiceprint account stores stored data information, which may be the user's historical evaluation data. After the target voiceprint account is determined, the stored data information in the target voiceprint account is accessed, and the target query data is determined according to the voice command. The target query data refers to the query data finally determined for the user.

[0039] In the above embodiments, by utilizing the uniqueness of voiceprints, different voiceprint accounts are opened for different voiceprints. When a user needs to query data, they only need to issue a voice command to quickly and accurately query the target data, which has high query efficiency and improves the reuse rate of stored data information stored in the target voiceprint account.

[0040] like Figure 2 As shown above, in the above Figure 1 Based on the illustrated embodiment, in an exemplary embodiment of the present invention, step 20, determining the target voiceprint account based on the voice command and the stored voiceprint account, may specifically include the following steps:

[0041] Step 201: Perform semantic recognition on the voice command and determine the semantic recognition result.

[0042] In one embodiment, the semantic recognition result is the result obtained by semantically recognizing the voice command. Specifically, a pre-trained semantic recognition model is set up. This model takes the voice command as input and the semantic recognition result as output. Therefore, after obtaining the voice command, inputting the voice command into the semantic recognition model can determine the semantic recognition result.

[0043] Step 202: If there is no object information in the semantic recognition result, the target voiceprint account is determined from the stored voiceprint accounts based on the current voiceprint features corresponding to the voice command.

[0044] In one embodiment, after obtaining the semantic recognition result, it is determined whether object information exists in the semantic recognition result. Object information refers to information about other voiceprint accounts that the current user wants to access. If no object information exists in the semantic recognition result, meaning the user wants to access their own voiceprint account, the target voiceprint account is determined from the stored voiceprint accounts based on the current voiceprint features corresponding to the voice command. Specifically, each stored voiceprint account carries stored voiceprint features. The current voiceprint features corresponding to the voice command are compared with the stored voiceprint features to determine the stored voiceprint feature with the highest similarity to the current voiceprint feature. The stored voiceprint account corresponding to the determined highest similarity stored voiceprint feature is then identified as the target voiceprint account.

[0045] Step 203: If object information exists in the semantic recognition result, then the target voiceprint account is determined based on the object information and the stored voiceprint account.

[0046] In one embodiment, if object information is present in the semantic recognition result, it indicates that the user wants to access stored data information in other voiceprint accounts. In this case, the target voiceprint account can be determined based on the object information and the stored voiceprint account. Specifically, the stored voiceprint account is bound to object information. For example, user A is bound to stored voiceprint account A, user B is bound to stored voiceprint account B, and user C is bound to stored voiceprint account C. When user A issues the voice command "A place that user C thinks is suitable for daydreaming," the semantic recognition result of this voice command contains object information, namely user C. Based on the object information user C, the target voiceprint account is determined to be stored voiceprint account C. Therefore, the stored data information in user C's corresponding stored voiceprint account C helps user A find a suitable place to daydream and determines the target query data.

[0047] In one possible implementation, if object information exists in the semantic recognition result, determining the target query data based on the voice command and the stored data information in the target voiceprint account includes: determining the open permissions of the target voiceprint account; if the open permissions indicate that the user has access to the target voiceprint account, then the target query data is determined based on the voice command and the stored data information in the target voiceprint account. To protect user privacy, users are allowed to set different open permissions for their corresponding voiceprint accounts, such as fully open, open to friends, and closed. Full open means everyone else can access it; open to friends means only those with a friend relationship with the voiceprint account are allowed access; and closed means no access is allowed. When the target voiceprint account has fully open permissions, the open permissions indicate that the user has access to the target voiceprint account. When the target voiceprint account has open permissions for friends, the current voiceprint account is determined based on the current voiceprint feature corresponding to the voice command, and it is determined whether there is a friend relationship between the current voiceprint account and the target voiceprint account. If so, the open permissions indicate that the user has access to the target voiceprint account.

[0048] It should be noted that in the above embodiments, users are allowed to access the stored voiceprint accounts corresponding to other users. In another possible implementation, users are only allowed to access their own corresponding voiceprint accounts. In this case, step 20, which determines the target voiceprint account based on the voice command and the stored voiceprint account, includes: determining the target voiceprint account based on the current voiceprint feature corresponding to the voice command and the stored voiceprint feature carried by the stored voiceprint account.

[0049] In the above embodiments, after semantic recognition of the voice command, the target voiceprint account that the user wants to access is determined based on whether object information exists in the semantic recognition result. When object information exists in the semantic recognition result, the user is allowed to access the target voiceprint account corresponding to the object information, thereby improving user convenience and enhancing user experience.

[0050] like Figure 3 As shown, in an exemplary embodiment of the present invention, when a semantic recognition result exists, the 30 determines the target query data based on the voice command and the stored data information in the target voiceprint account, including:

[0051] Step 301: Determine the user intent based on the semantic recognition result corresponding to the voice command.

[0052] Step 302: If the user's intent meets the preset conditions, then the target query data is determined based on the semantic recognition result and the stored data information in the target voiceprint account.

[0053] In one embodiment, voice commands can be used not only to query data but also to store evaluation voice messages. For example, when a user issues the voice command "The steak at this restaurant is delicious," the user intends to store the evaluation voice message. When the user issues the voice command "A place with delicious steak," the user intends to query the data. Therefore, it is necessary to determine the user's intent based on the semantic recognition results. The user's intent refers to the operation the user wants to perform, including query intent and storage intent. Preset conditions are used to filter the user's intent, selecting voice commands with the intent to query. Specifically, the preset conditions can be set to indicate that the user's intent is to query. When the user's intent is to query, a data query is performed based on the semantic recognition results and the data stored in the target voiceprint account to determine the target query data.

[0054] In one possible implementation, step 302 includes: if the user's intent is a query intent, determining the user's fourth current location information; and determining target query data based on the fourth current location information, the semantic recognition result, and the stored data information in the target voiceprint account. That is, when determining the target query data, the user's location, the semantic recognition result corresponding to the voice command, and the stored data information are comprehensively considered to ensure that the target location information in the determined target query data is close to the fourth current location information. For example, if there are multiple matching stored data information that match the semantic recognition result, the distance between the location information in each matching stored data information and the fourth current location information is determined, and the matching stored data information with the smallest distance to the fourth current location information is determined as the target query data.

[0055] In the above embodiments, user intent is distinguished based on semantic recognition results. Only when the user intent is a query intent is the target query data determined based on the semantic recognition results and the stored data information in the target voiceprint account. This accurately grasps the user intent, performs appropriate operations based on the user intent, and improves user convenience.

[0056] like Figure 4 As shown above, in the above Figure 3 Based on the illustrated embodiment, in an exemplary embodiment of the present invention, the method may further include the following steps:

[0057] Step 303: If the user's intent does not meet the preset conditions, then determine the first current location information.

[0058] Step 304: Based on the semantic recognition result and the first current location information, update the stored data information in the target voiceprint account.

[0059] In one embodiment, when the user's intent does not meet preset conditions, it indicates that the user's intent is a storage intent rather than a query intent. At this time, the first current location information is determined. The first current location information refers to the current location of the user at the current moment. Specifically, the first current location information can be obtained through the positioning system of the smart terminal. After obtaining the first current location information, in order to satisfy the user's storage intent, the semantic recognition result and the first current location information are stored as a single data set in the storage data information of the target voiceprint account to update the storage data information in the target voiceprint account.

[0060] In one possible implementation, the first current location information can be specific to the user's point of interest (POI) name, such as the name of a steakhouse. However, when using a smart terminal's positioning system, it may not be possible to directly locate the user's POI; for example, it might only be able to locate the name of an online store. In this case, the located online store name is first stored, and subsequent voice messages from the user are retrieved. Based on the store names and store characteristics (such as steak or grilled fish) mentioned in the voice messages, the stored online store location is further associated. Alternatively, the in-vehicle smart terminal can be used to extract the current navigation destination and determine whether it is a consumer-related POI, such as directly navigating to a steakhouse. If so, the consumer-related POI in the navigation destination is used as the first current location information. Of course, access permissions for photos stored on the user's mobile smart terminal can also be obtained to determine photos taken by the user within a preset time period before the current moment. These photos are then used to perform a full-network search to accurately determine the POI name, and this POI name is stored as the first current location information.

[0061] In the above embodiments, when the user's intent is to store, the semantic analysis result corresponding to the user's voice command and the first current location information are stored in the user's corresponding target voiceprint account. This can effectively store the user's voice evaluation data, and when the user has a query intent, the user's stored voice evaluation data can be quickly and accurately queried.

[0062] In one possible application scenario, user A eats steak at location a and decides that the steak is good and worth noting. They then say to their phone, "The steak here is delicious." The phone's voice capture device picks up this voice command, uploads it to the cloud, and uses a semantic recognition model set up in the cloud to determine the semantic recognition result. This result might be "here," "steak," or "delicious." Since this result doesn't contain object information, the target voiceprint account is determined based on the current voiceprint characteristics of the voice command. Given that the user's intent is storage, the phone receives the first current location information and then stores the time, the first current location information, and the semantic recognition result as storage data in the target voiceprint account. After a period of time, a user might want to find a good steak restaurant and can issue the voice command "A good steak restaurant." The voice capture device will then collect this command and upload it to the cloud. The cloud will analyze the voice command using a semantic recognition model to obtain the semantic recognition result. Since the semantic recognition result does not contain object information, the target voiceprint account is determined based on the current voiceprint characteristics of the voice command. Given that the user's intent is a query, the semantic recognition result is matched with the stored data in the target voiceprint account to determine the previously recorded data related to "steak" and "good." After determining the target query data, it can be displayed on the mobile device, showing the recording time, recorded content, and the first current location information of the record.

[0063] It should be noted that in the above embodiments, semantic recognition results are used to determine the user's intent. In another possible implementation, query command icons and store command icons are provided on the application interface. That is, when the user clicks different icons to input voice commands, different operations will be performed. In this case, the method includes:

[0064] The system acquires the user's voice command; determines the type of the voice command; if the voice command is a query command, it determines the target voiceprint account based on the voice command and the stored voiceprint account; and determines the target query data based on the voice command and the stored data information in the target voiceprint account. If the voice command is a stored command, it determines the first current location information and updates the stored data information in the target voiceprint account based on the semantic recognition result and the first current location information. Thus, by setting different voice input interfaces, the purpose of identifying user intent can also be achieved.

[0065] like Figure 5 As shown above, in the above Figure 1 Based on the illustrated embodiment, in an exemplary embodiment of the present invention, the step 20 determines the target voiceprint account based on the voice command and the stored voiceprint account, including:

[0066] Step 203: Determine the account identifier carried by the voice command.

[0067] In one embodiment, the account identifier refers to the account information corresponding to the device that issues the voice command, such as a mobile device number or user account information set by the user.

[0068] Step 204: Determine the bound voiceprint account of the account identifier in the stored voiceprint accounts.

[0069] In one embodiment, each stored voiceprint account is allowed to be bound to an account identifier. That is, when a voice command is obtained, the stored voiceprint account that is bound to the account identifier carried by the voice command is determined, i.e., the bound voiceprint account is determined.

[0070] Step 205: If the current voiceprint feature corresponding to the voice command matches the stored voiceprint feature corresponding to the bound voiceprint account, then the bound voiceprint account is determined to be the target voiceprint account.

[0071] In one embodiment, the similarity between the current voiceprint feature corresponding to the voice command and the bound voiceprint feature is determined. If the determined similarity is greater than a set value, the current voiceprint feature corresponding to the voice command matches the stored voiceprint feature corresponding to the bound voiceprint account. At this time, the bound voiceprint account is the target voiceprint account.

[0072] In one possible application scenario, when a user first opens the query application set up in the vehicle's infotainment system, a user account information setting interface is displayed. After the user enters their user information, the obtained user account information is used as an account identifier, and the user is prompted to record a voice message to create a voiceprint account for the first-time user. The created voiceprint account is stored and bound to the account identifier. When uploading using the same account identifier, the system first determines whether the stored voiceprint features corresponding to the bound voiceprint account that is already bound to that account identifier match the current voiceprint features corresponding to the voice command. If they match, the target voiceprint account can be directly identified, thus improving the efficiency of target voiceprint account identification.

[0073] like Figure 6 As shown above, in the above Figure 5 Based on the illustrated embodiment, in an exemplary embodiment of the present invention, the method further includes:

[0074] Step 206: If the current voiceprint feature corresponding to the voice command does not match the stored voiceprint feature corresponding to the bound voiceprint account, then determine the matching voiceprint account that matches the current voiceprint feature corresponding to the voice command from the stored voiceprint accounts.

[0075] In one embodiment, if the current voiceprint feature corresponding to a voice command does not match the stored voiceprint feature corresponding to the bound voiceprint account, it proves that another user has uploaded the voice command using the current user's account. Therefore, to facilitate operations for other users, a matching voiceprint account that matches the current voiceprint feature corresponding to the voice command is determined from the stored voiceprint accounts. In other words, even if different users use the same device to issue voice commands, different stored voiceprint accounts can be matched based on the voiceprints of different users, allowing different users to use the same account to perform subsequent operations on their respective corresponding voiceprint accounts, further improving user convenience.

[0076] In one possible application scenario, users A, B, and C are having a meal together, and all three uploaded voice commands using user A's phone. When the cloud receives the three voice commands, it identifies the account identifier 'm' carried by each command. Since user A's stored voiceprint account is bound to this identifier 'm', when matching the stored voiceprint features in the bound voiceprint account with the voice commands uploaded by user A, if a match is found, then user A's stored voiceprint account is identified as the target voiceprint account. If the stored voiceprint features in the bound voiceprint account are then matched with the voice commands uploaded by user B or user C, and a mismatch is found, then the stored voiceprint accounts that match the current voiceprint features corresponding to user B's or user C's voice commands are identified. These matched voiceprint accounts are user B's and user C's stored voiceprint accounts.

[0077] Step 207: Determine the second current location information.

[0078] In one embodiment, the second current location information refers to the location of the device that issued the voice command at the current moment.

[0079] Step 208: Based on the semantic recognition result corresponding to the voice command and the second current location information, update the stored data information in the matched voiceprint account.

[0080] In the above embodiments, semantic recognition is performed on the voice commands to determine the corresponding semantic recognition result. This semantic recognition result and the second current location information are then stored as storage data in the matching voiceprint account. This allows the same account to be used to update the stored data in different stored voiceprint accounts, improving user convenience.

[0081] It should be noted that, in one possible implementation, not only can different users use the same account to update stored data information in different stored voiceprint accounts, but users can also use the same account to query stored data information in different stored voiceprint accounts. For example, after determining and matching a voiceprint account, the semantic recognition result corresponding to the voice command is determined; if the user intent corresponding to the semantic recognition result is a query intent, then the matched voiceprint account is determined as the target voiceprint account, that is, the target query data is determined based on the voice command and the stored data information in the matched voiceprint account. If the user intent corresponding to the semantic recognition result is a storage intent, then the second current location information is determined; based on the semantic recognition result corresponding to the voice command and the second current location information, the stored data information in the matched voiceprint account is updated.

[0082] To further improve user convenience, in an exemplary embodiment of the present invention, the method further includes: step 209, establishing a friend access relationship between the bound voiceprint account and the matched voiceprint account. After determining that an account has issued voice commands corresponding to multiple stored voiceprint accounts, a friend access relationship is established between the bound voiceprint account and the matched voiceprint account. Based on this access relationship, resources are shared between the bound voiceprint account and the matched voiceprint account, and they have mutual access permissions.

[0083] like Figure 7 As shown above, in the above Figure 1 Based on the illustrated embodiment, in an exemplary embodiment of the present invention, the method further includes:

[0084] Step 210: If there is no target voiceprint account in the stored voiceprint accounts that matches the current voiceprint feature corresponding to the voice command, then a temporary voiceprint account is set up.

[0085] Step 211: Determine the third current location information.

[0086] Step 212: Based on the semantic recognition result corresponding to the voice command and the third current location information, determine the storage data information of the temporary voiceprint account.

[0087] In one embodiment, there may be a situation where the stored voiceprint accounts do not contain a voiceprint account that matches the current voiceprint features corresponding to the voice command. This means the user corresponding to the voice command is a new user using the service for the first time. Therefore, a temporary voiceprint account is created for this new user. The third current location information refers to the current user's location at the current moment. Since this user is a new user, the voice command is stored, meaning the semantic recognition result corresponding to the voice command and the third current location information are stored as data in the temporary voiceprint account. It should be noted that the stored data information in the temporary voiceprint account is not only temporarily saved but also permanently stored. When the new user uses the voice command again, a corresponding temporary voiceprint account will be determined based on the new user's voiceprint features. This continues until the new user uses the settings application to create a new voiceprint account. After prompting the user to input a voice command, a temporary voiceprint account will be automatically matched for the user, allowing the new user to bind it to an account identifier.

[0088] In an exemplary embodiment of the present invention, after determining the target query data, the method further includes:

[0089] The target query data can be displayed for user viewing. Alternatively, after the target query data is determined, it can be read aloud. Alternatively, after the target query data is determined, it can be read aloud while simultaneously displaying the target query data. Alternatively, after the target query data is determined, a navigation route can be determined based on the target location information within the target query data. Alternatively, after the target query data is determined, a navigation route can be determined based on the target location information within the target query data, while simultaneously displaying and reading aloud the target query data.

[0090] In an exemplary embodiment of the present invention, after determining the target query data, the method further includes:

[0091] The target query data is displayed based on a preset interface;

[0092] The target application is launched in response to the user's operation command on the preset interface.

[0093] In the above embodiments, after the target query data is determined, it is displayed on a preset interface, allowing the user to make selections. Based on the user's operation instructions on the preset interface, a target application is launched. The target application refers to the application that supports the function selected by the user on the preset interface; different user selections result in different target applications. For example, if the user determines to navigate to the target location information in the target query data, an application supporting navigation is launched; if the user determines to query related information, an application supporting query functionality is launched. This provides the user with choices, meets various user needs, and offers convenience.

[0094] Exemplary device

[0095] Based on the same concept as the embodiments of the method of the present invention, such as Figure 8 As shown, this embodiment of the invention also provides a target data query device, which specifically includes the following modules:

[0096] The instruction acquisition module 81 is used to acquire the user's voice commands;

[0097] Account determination module 82 is used to determine the target voiceprint account based on the voice command and the stored voiceprint account;

[0098] The data query module 83 is used to determine the target query data based on the voice command and the stored data information in the target voiceprint account.

[0099] In an exemplary embodiment of the present invention, the account determination module includes:

[0100] A speech recognition unit is used to perform semantic recognition on the speech command and determine the semantic recognition result;

[0101] The first determining unit is used to determine the target voiceprint account in the stored voiceprint accounts based on the current voiceprint features corresponding to the voice command if there is no object information in the semantic recognition result.

[0102] In an exemplary embodiment of the present invention, the account determination module further includes:

[0103] The second determining unit is used to determine the target voiceprint account based on the object information and the stored voiceprint account if the semantic recognition result contains object information.

[0104] In an exemplary embodiment of the present invention, the data query module includes:

[0105] An intent recognition unit is used to determine the user's intent based on the semantic recognition result corresponding to the voice command;

[0106] The third determining unit is used to determine the target query data based on the semantic recognition result and the stored data information in the target voiceprint account if the user intent meets the preset conditions.

[0107] In an exemplary embodiment of the present invention, the data query module further includes:

[0108] A location determination unit is used to determine first current location information if the user's intent does not meet the preset conditions;

[0109] The data storage unit is used to update the stored data information in the target voiceprint account based on the semantic recognition result and the first current location information.

[0110] In an exemplary embodiment of the present invention, the account determination module includes:

[0111] An identifier determination unit is used to determine the account identifier carried by the voice command;

[0112] The account binding determination unit is used to determine the account identifier bound to the voiceprint account in the stored voiceprint accounts;

[0113] The fourth determining unit is used to determine the bound voiceprint account as the target voiceprint account if the current voiceprint feature corresponding to the voice command matches the stored voiceprint feature corresponding to the bound voiceprint account.

[0114] In an exemplary embodiment of the present invention, the account determination module further includes:

[0115] The fifth determining unit is used to determine, if the current voiceprint feature corresponding to the voice command does not match the stored voiceprint feature corresponding to the bound voiceprint account, a matching voiceprint account that matches the current voiceprint feature corresponding to the voice command from the stored voiceprint accounts.

[0116] The sixth determining unit is used to determine the second current position information;

[0117] The data update unit is used to update the stored data information in the matching voiceprint account based on the semantic recognition result corresponding to the voice command and the second current location information.

[0118] In an exemplary embodiment of the present invention, the account determination module further includes:

[0119] The relationship establishment unit is used to establish a friend access relationship between the bound voiceprint account and the matched voiceprint account.

[0120] In an exemplary embodiment of the present invention, the apparatus further includes:

[0121] The temporary voiceprint determination module is used to establish a temporary voiceprint account if there is no target voiceprint account in the stored voiceprint accounts that matches the current voiceprint feature corresponding to the voice command.

[0122] The location information determination module is used to determine the third current location information;

[0123] The data storage module is used to determine the storage data information of the temporary voiceprint account based on the semantic recognition result corresponding to the voice command and the third current location information.

[0124] In an exemplary embodiment of the present invention, the apparatus further includes: a post-processing module;

[0125] The subsequent processing module is used to display the target query data; or, the subsequent processing module is used to announce the target query data aloud; or, the subsequent processing module is used to determine a navigation route based on the target location information in the target query data; or, the subsequent processing module is used to display the target query data and announce the target query data aloud; or, the subsequent processing module is used to determine a navigation route based on the target location information in the target query data and display the target query data; or, the subsequent processing module is used to determine a navigation route based on the target location information in the target query data and announce the target query data aloud; or, the subsequent processing module is used to determine a navigation route based on the target location information in the target query data, display the target query data and announce the target query data aloud; or, the subsequent processing module is used to display the target query data on a preset interface; and to launch the target application in response to the user's operation command on the preset interface.

[0126] Exemplary electronic devices

[0127] Figure 9 A block diagram of an electronic device according to an embodiment of the present invention is shown.

[0128] like Figure 9 As shown, the electronic device 100 includes one or more processors 101 and memory 102.

[0129] The processor 101 may be a central processing unit (CPU) or other form of processing unit with data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device 100 to perform desired functions.

[0130] The memory 102 may include one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may include, for example, random access memory (RAM) and / or cache memory. The non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and the processor 101 may execute the program instructions to implement the target data query method and / or other desired functions described in the various embodiments of the present invention above.

[0131] In one example, the electronic device 100 may also include an input device 103 and an output device 104, which are interconnected via a bus system and / or other forms of connection mechanism (not shown).

[0132] Of course, for the sake of simplicity, Figure 9 Only some of the components of the electronic device 100 relevant to the present invention are shown, omitting components such as buses, input / output interfaces, etc. In addition, the electronic device 100 may include any other suitable components depending on the specific application.

[0133] Exemplary computer program products and computer-readable storage media

[0134] In addition to the methods and devices described above, embodiments of the present invention may also be computer program products, which include computer program instructions that, when executed by a processor, cause the processor to perform the steps in the target data query methods according to various embodiments of the present invention described in the "Exemplary Methods" section above.

[0135] The computer program product can be written in any combination of one or more programming languages ​​to perform the operations of the embodiments of the present invention. The programming languages ​​include object-oriented programming languages ​​such as Java and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computing device, partially on the user's computing device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0136] Furthermore, embodiments of the present invention may also be computer-readable storage media storing computer program instructions thereon, which, when executed by a processor, cause the processor to perform the steps in the target data query methods according to various embodiments of the present invention described in the "Exemplary Methods" section above.

[0137] The computer-readable storage medium may be any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may, for example, include, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatuses, or devices, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: electrical connections having one or more wires, portable disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0138] The basic principles of the present invention have been described above with reference to specific embodiments. However, it should be noted that the advantages, benefits, and effects mentioned in the present invention are merely examples and not limitations, and should not be considered as essential features of each embodiment of the present invention. Furthermore, the specific details of the invention described above are for illustrative and facilitative purposes only, and are not limitations. These details do not limit the present invention to the necessity of employing the specific details described above.

[0139] The block diagrams of devices, apparatuses, devices, and systems involved in this invention are merely illustrative examples and are not intended to require or imply that they must be connected, arranged, or configured in the manner shown in the block diagrams. As those skilled in the art will recognize, these devices, apparatuses, devices, and systems can be connected, arranged, and configured in any manner. Words such as “comprising,” “including,” “having,” etc., are open-ended terms meaning “including but not limited to,” and are used interchangeably with them. The terms “or” and “and” as used herein refer to the terms “and / or,” and are used interchangeably with them unless the context clearly indicates otherwise. The term “such as” as used herein refers to the phrase “such as but not limited to,” and is used interchangeably with it.

[0140] It should also be noted that in the apparatus, device, and method of the present invention, the components or steps can be disassembled and / or recombined. These disassemblies and / or recombinations should be considered as equivalent solutions of the present invention.

[0141] The above description of aspects of the invention is provided to enable any person skilled in the art to make or use the invention. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein can be applied to other aspects without departing from the scope of the invention. Therefore, the invention is not intended to be limited to the aspects shown herein, but rather to be carried out within the widest scope consistent with the principles and novel features of the invention herein.

[0142] The above description has been given for purposes of illustration and description. Furthermore, this description is not intended to limit the embodiments of the invention to the forms described herein. Although numerous exemplary aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, alterations, additions, and sub-combinations therein.

Claims

1. A target data query method, characterized by, Specifically comprising the following steps: Obtaining a voice instruction of a user; Determining a target voiceprint account based on the voice instruction and a stored voiceprint account; Determining target query data based on the voice instruction and stored data information in the target voiceprint account; The step of determining target query data based on the voice instruction and stored data information in the target voiceprint account comprises: Determining a user intention based on a semantic recognition result corresponding to the voice instruction; If the user intention is a query intention, determining target query data based on the semantic recognition result and stored data information in the target voiceprint account, the target query data comprising target location information; If the user intention is a storage intention, determining first current location information and updating the stored data information in the target voiceprint account based on the semantic recognition result and the first current location information; Determining a navigation route based on the target location information in the target query data.

2. The method of claim 1, wherein the step of determining a target voiceprint account based on the voice instruction and a stored voiceprint account comprises: Performing semantic recognition on the voice instruction to determine a semantic recognition result; If there is no object information in the semantic recognition result, determining a target voiceprint account in the stored voiceprint account based on current voiceprint features corresponding to the voice instruction.

3. The method of claim 2, further comprising: If there is object information in the semantic recognition result, determining a target voiceprint account based on the object information and the stored voiceprint account.

4. The method of claim 1, wherein the step of determining a target voiceprint account based on the voice instruction and a stored voiceprint account comprises: Determining an account identifier carried by the voice instruction; Determining a binding voiceprint account of the account identifier in the stored voiceprint account; If current voiceprint features corresponding to the voice instruction match stored voiceprint features corresponding to the binding voiceprint account, determining the binding voiceprint account as the target voiceprint account.

5. The method of claim 4, further comprising: If the current voiceprint features corresponding to the voice instruction do not match the stored voiceprint features corresponding to the binding voiceprint account, determining a matching voiceprint account in the stored voiceprint account that matches the current voiceprint features corresponding to the voice instruction; Determining second current location information; Updating stored data information in the matching voiceprint account based on a semantic recognition result corresponding to the voice instruction and the second current location information.

6. The method of claim 5, further comprising: Establishing a friend access relationship between the binding voiceprint account and the matching voiceprint account.

7. The method of claim 1, further comprising: If there is no target voiceprint account in the stored voiceprint account that matches the current voiceprint features corresponding to the voice instruction, setting up a temporary voiceprint account; Determining third current location information; Determining stored data information of the temporary voiceprint account based on a semantic recognition result corresponding to the voice instruction and the third current location information. 8.The method of any one of claims 1-7, after determining the target query data, the method further comprises: displaying the target query data; and / or, voice broadcasting the target query data. 9.The method of any one of claims 1-7, after determining the target query data, the method further comprises: displaying the target query data based on a preset interface; and starting a target application program in response to a user operation instruction on the preset interface. Specifically comprising the following modules:

10. A target data query apparatus characterized by comprising: an instruction obtaining module, configured to obtain a voice instruction of a user; an account determining module, configured to determine a target voiceprint account based on the voice instruction and a stored voiceprint account; a data query module, configured to determine target query data based on the voice instruction and stored data information in the target voiceprint account; and the data query module comprises: an intention identifying unit, configured to determine a user intention based on a semantic recognition result corresponding to the voice instruction; a unit configured to, if the user intention is a query intention, determine the target query data based on the semantic recognition result and the stored data information in the target voiceprint account, the target query data comprising target location information; a unit configured to, if the user intention is a storage intention, determine first current location information; a data storage unit, configured to update the stored data information in the target voiceprint account based on the semantic recognition result and the first current location information; and a unit configured to determine a navigation route based on the target location information in the target query data. 11.A computer readable storage medium, the storage medium storing a computer program, the computer program being configured to execute the target data query method of any one of claims 1-9. 12.An electronic device, comprising: a processor; a memory configured to store executable instructions of the processor; and the processor, configured to read the executable instructions from the memory and execute the instructions to implement the target data query method of any one of claims 1-9. ​

Images