Application control method and device, electronic equipment and storage medium

Abstract

The invention provides an application control method and device, electronic equipment and a storage medium, and relates to the technical field of computers, in particular to the technical field of artificial intelligence such as deep learning and large models. According to the specific scheme, under the condition that a first voice input by a user is received, the first voice is recognized, a target intention and a target object of the first voice are determined, then a plurality of reference objects are obtained from a controlled application based on the target object, and the reference objects are sequentially broadcasted, and updating a session corresponding to any reference object in the controlled application based on the target intention under the condition that a second voice for confirming any reference object is received.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technology, in particular to the field of artificial intelligence technology such as deep learning and large models, and specifically to an application control method, device, electronic device and storage medium. Background Art

[0002] With the continuous development of computer technology, the functions of smart terminals are becoming more and more powerful and their application fields are becoming more and more extensive. However, for people with disabilities, it is still difficult to use various social applications conveniently. How to improve the convenience of using smart terminals for people with disabilities is an urgent problem to be solved. Summary of the invention

[0003] The present disclosure aims to solve one of the technical problems in the related art at least to some extent.

[0004] The first embodiment of the present disclosure provides an application control method, including:

[0005] When receiving a first voice input by a user, recognizing the first voice and determining a target intent and a target object of the first voice;

[0006] Based on the target object, obtaining a plurality of reference objects from the controlled application;

[0007] broadcasting the multiple reference objects in sequence;

[0008] When a second voice for confirming any reference object is received, a session corresponding to any reference object in the controlled application is updated based on the target intention.

[0009] The second aspect of the present disclosure provides an application control device, including:

[0010] A recognition module, configured to recognize a first voice input by a user and determine a target intent and a target object of the first voice when the first voice is received;

[0011] An acquisition module, used for acquiring a plurality of reference objects from a controlled application based on the target object;

[0012] A reporting module, used for reporting the multiple reference objects in sequence;

[0013] An updating module is used to update a session corresponding to any reference object in the controlled application based on the target intention when a second voice for confirming any reference object is received.

[0014] The third aspect of the present disclosure provides a computer device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the application control method provided in the first aspect of the present disclosure is implemented.

[0015] The fourth aspect of the present disclosure provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, the application control method provided in the first aspect of the present disclosure is implemented.

[0016] The fifth aspect of the present disclosure provides a computer program product, including a computer program. When the computer program is executed by a processor, it implements the application control method provided in the first aspect of the present disclosure.

[0017] The application control method, device, electronic device and storage medium provided by the present disclosure have the following beneficial effects:

[0018] In the disclosed embodiment, first, when a first voice input by a user is received, the first voice is recognized to determine the target intent and target object of the first voice, and then, based on the target object, multiple reference objects are obtained from the controlled application, and the multiple reference objects are broadcasted in sequence, and then, when a second voice for confirming any reference object is received, the session corresponding to any reference object in the controlled application is updated based on the target intent. Thus, by recognizing the first voice input by the user, determining the user intent and the target object, multiple reference objects close to the target object are determined from the controlled application and broadcasted, and after receiving the voice for confirming any reference object, the session of the reference object in the controlled application is updated based on the user intent, thereby improving the convenience and reliability of application control and enhancing the user experience.

[0019] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure.

[0021] Figure 1 A flowchart of an application control method provided by an embodiment of the present disclosure;

[0022] Figure 2 A flowchart of an application control method provided by an embodiment of the present disclosure;

[0023] Figure 3A flowchart of an application control method provided by an embodiment of the present disclosure;

[0024] Figure 4 A flowchart of an application control method provided by an embodiment of the present disclosure;

[0025] Figure 5 A flowchart of an application control method provided by an embodiment of the present disclosure;

[0026] Figure 6 A flowchart of an application control method provided by an embodiment of the present disclosure;

[0027] Figure 7 A schematic diagram of the structure of an application control device provided in an embodiment of the present disclosure;

[0028] Figure 8 A block diagram of an exemplary computer device suitable for implementing embodiments of the present disclosure is shown. DETAILED DESCRIPTION

[0029] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0030] The present disclosure relates to the fields of artificial intelligence technologies such as deep learning and large models.

[0031] Artificial Intelligence (AI) is a new technical science that studies and develops theories, methods, technologies and application systems for simulating, extending and expanding human intelligence.

[0032] Deep Learning (DL) is the process of learning the inherent laws and representation levels of sample data. The information obtained in the learning process is very helpful for interpreting data such as text, images, and sounds. The ultimate goal of deep learning is to enable machines to have analytical learning capabilities like humans and to recognize data such as text, images, and sounds.

[0033] The large model can also be called the Foundation Model. The model extracts knowledge through billions of corpora or images, learns and then produces a large model with billions of parameters.

[0034] In the technical solution of the present disclosure, the collection, storage, use, processing, transmission, provision and disclosure of user personal information involved are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0035] The following describes the application control method, device, electronic device, and storage medium according to the embodiments of the present disclosure with reference to the accompanying drawings.

[0036] Figure 1 A flowchart of an application control method provided by an embodiment of the present disclosure.

[0037] like Figure 1 As shown, the application control method may include the following steps:

[0038] Step 101: upon receiving a first voice input by a user, recognize the first voice and determine a target intention and a target object of the first voice.

[0039] It should be noted that the specific content of the first voice can be determined according to the specific needs of the user, and this disclosure does not limit this.

[0040] It should be noted that the target object may be different depending on the target intent. For example, when the target intent is to obtain a list of contacts in an application, the target object may be the information of all contacts, and when the target intent is to send a message to contact A in the application, the target object may be contact A in the application. This disclosure does not limit this.

[0041] In the present disclosure, when the conversation service receives the first voice input by the user, it can start the voice conversion service to convert the first voice into corresponding text information, and then start the recognition service to recognize the text information and determine the target intention and target object of the first voice. The present disclosure does not limit this.

[0042] Among them, the conversation service can start other services based on the user's request, which can be pre-set and the present disclosure does not limit this.

[0043] It should be noted that when the recognition service is started and the text information converted from the first voice is recognized, the text information can be spliced ​​into prompt information, and the model service can be started to input the prompt information into the model to obtain the target intention and target object of the first voice output by it. This disclosure does not limit this.

[0044] The model service may be a large model service of any type and structure, for example, a GPT type model service, which is not limited in the present disclosure.

[0045] Among them, GPT is the abbreviation of Generative Pre-Training Transformer (GPT), which is a deep learning model.

[0046] Optionally, before receiving the first voice input by the user, when it is detected that a preset button in the device is touched, it can be determined that the user currently needs to input a voice command. At this time, a voice collection service can be started to receive the first voice input by the user. The present disclosure does not limit this.

[0047] Optionally, before receiving the first voice input by the user, the voice collection service can be started to receive the first voice when the movement trajectory and / or frequency of the device are monitored to meet the preset conditions. For example, when the movement trajectory of the device is monitored to meet the trajectory requirements when starting the voice collection service, and / or the frequency reaches the frequency threshold value for starting the voice collection service (such as shaking), it can be determined that the conditions for starting the voice collection service are met, and the voice collection service is started. This disclosure does not limit this.

[0048] The preset condition may be a prerequisite for determining the start of the voice collection service, which may be pre-set or determined according to actual needs, and may include any content. For example, the preset condition may include the movement trajectory requirements of the device before starting the voice collection service, and / or the frequency threshold of shaking the device, etc., which are not limited in the present disclosure.

[0049] In the present disclosure, before receiving the first voice input by the user, the voice collection service is started in a variety of ways, thereby increasing the flexibility of starting the voice collection service and improving the user experience.

[0050] Step 102: Acquire multiple reference objects from the controlled application based on the target object.

[0051] The controlled application may be an application where the target object is located, and may be any type of application. For example, the controlled application may be a social application, which is not limited in the present disclosure.

[0052] The reference object may be an object having a high similarity to the target object.

[0053] In the present disclosure, after determining the target object of the first voice, multiple reference objects can be obtained from the controlled application based on the target object, thereby providing conditions for confirming the reliability of the target object from the reference objects.

[0054] Optionally, before acquiring multiple reference objects from the controlled application based on the target object, when the controlled application is included in the first voice, the controlled application may be directly determined based on the first voice, which is not limited in the present disclosure.

[0055] Optionally, before obtaining multiple reference objects from the controlled application based on the target object, if the controlled application is not included in the first voice, the controlled application input indication can also be played, and the controlled application can be determined based on the received fourth voice, which is not limited in the present disclosure.

[0056] The fourth voice may be a voice used to determine the controlled application.

[0057] In the present disclosure, before obtaining multiple reference objects from the controlled application based on the target object, the controlled application can be determined in a corresponding manner regardless of whether the first voice contains the controlled application, thereby improving the flexibility and reliability of the method for determining the controlled application.

[0058] Step 103: broadcast multiple reference objects in sequence.

[0059] In the present disclosure, after obtaining multiple reference objects from the controlled application, the multiple reference objects can be broadcasted to the user in sequence, so that the user can easily confirm the target object.

[0060] It should be noted that after determining multiple reference objects, when multiple applicants are broadcasted in sequence, when none of the current multiple reference objects have been confirmed by the user as reference objects of the target object, multiple new reference objects can continue to be acquired, and so on, until the user confirms any reference object as the target object. The present disclosure does not limit this.

[0061] Step 104 : When a second voice for confirming any reference object is received, a session corresponding to any reference object in the controlled application is updated based on the target intent.

[0062] In the present disclosure, after multiple reference objects are broadcast to the user in sequence, the conversation service can determine that any reference object is the target object when receiving a second voice for confirming any reference object. At this time, the conversation corresponding to any reference object in the controlled application can be updated based on the target intention, thereby improving the reliability of application control and the convenience of user conversations.

[0063] It should be noted that after the conversation corresponding to any reference object is updated, when a voice input by the user is received to indicate the end of the current conversation, the current conversation process can be exited after the voice recognition, or when it is detected that a preset button is touched, the conversation process can be exited, or when it is detected that the device has met an action condition (such as shaking), the conversation process can be exited. The present disclosure does not limit this.

[0064] In the disclosed embodiment, first, when a first voice input by a user is received, the first voice is recognized to determine the target intent and target object of the first voice, and then, based on the target object, multiple reference objects are obtained from the controlled application, and the multiple reference objects are broadcasted in sequence, and then, when a second voice for confirming any reference object is received, the session corresponding to any reference object in the controlled application is updated based on the target intent. Thus, by recognizing the first voice input by the user, determining the user intent and the target object, multiple reference objects close to the target object are determined from the controlled application and broadcasted, and after receiving the voice for confirming any reference object, the session of the reference object in the controlled application is updated based on the user intent, thereby improving the convenience and reliability of application control and enhancing the user experience.

[0065] Figure 2 A flowchart of an application control method provided by an embodiment of the present disclosure.

[0066] like Figure 2 As shown, the application control method may include the following steps:

[0067] Step 201: upon receiving a first voice input by a user, the first voice is recognized to determine a target intention and a target object of the first voice.

[0068] The specific implementation form of step 201 can refer to the detailed description in other embodiments of the present disclosure, and will not be described in detail here.

[0069] Step 202, determining a first pinyin sequence corresponding to the target object and a second pinyin sequence corresponding to each candidate object in the controlled application.

[0070] In the present disclosure, after determining the target object, in order to improve the accuracy of obtaining the reference object in the controlled application, the first pinyin sequence corresponding to the target object and the second pinyin sequence corresponding to each candidate object in the controlled application can be first determined.

[0071] It should be noted that the second pinyin sequence may be the same as the first pinyin sequence, or may be different from the first pinyin sequence, and the present disclosure does not limit this.

[0072] Step 203, determining the similarity between the first pinyin sequence and each second pinyin sequence.

[0073] In the present disclosure, after determining the first pinyin sequence corresponding to the target object and the second pinyin sequence corresponding to each candidate object in the controlled application, in order to accurately determine the target object from the candidate objects, the similarity between the first pinyin sequence and each second pinyin sequence can be first determined.

[0074] Optionally, when determining the similarity between the first Pinyin sequence and each second Pinyin sequence, the similarity between the second Pinyin sequence containing the same number of Pinyin letters as the first Pinyin sequence and the first Pinyin sequence can be determined, so that before determining the similarity between the Pinyin sequences of the candidate objects and the target object, the candidate objects are first screened to reduce the number of candidate objects for calculating similarity with the target object, reduce resource waste and improve computing efficiency. The present disclosure does not limit this.

[0075] Step 204: determine N candidate objects with the largest corresponding similarities as multiple reference objects, where N is an integer greater than 1.

[0076] It should be noted that the specific value of N may be related to the number of candidate objects with the greatest similarity, and the present disclosure does not limit this.

[0077] In the present disclosure, after determining the similarity between the first pinyin sequence and each second pinyin sequence, the candidate object with greater similarity has a higher degree of similarity to the target object and a greater probability of being the target object. At this time, the N candidate objects with the greatest corresponding similarities can be determined as multiple reference objects, thereby improving the reliability and accuracy of the determined reference objects.

[0078] Step 205: broadcast multiple reference objects in sequence.

[0079] Step 206: When a second voice for confirming any reference object is received, a session corresponding to any reference object in the controlled application is updated based on the target intent.

[0080] The specific implementation forms of step 205 to step 206 can refer to the detailed descriptions in other embodiments of the present disclosure, and will not be described in detail here.

[0081] In the disclosed embodiment, first, when receiving the first voice input by the user, the first voice is recognized, the target intent and target object of the first voice are determined, and then the first pinyin sequence corresponding to the target object and the second pinyin sequence corresponding to each candidate object in the controlled application are determined, and the similarity between the first pinyin sequence and each second pinyin sequence is determined, and then the N candidate objects with the largest similarity are determined as multiple reference objects, and the multiple reference objects are broadcasted in sequence, and finally, when receiving the second voice for confirming any reference object, the session corresponding to any reference object in the controlled application is updated based on the target intent. Thus, by recognizing the voice input by the user, determining the user intent and the target object, the pinyin sequence corresponding to the target object and the similarity between the pinyin sequence corresponding to each candidate object in the controlled application are determined, and the N candidate objects with the largest similarity are determined as reference objects and broadcasted, and after the user confirms that any reference object is the target object, the session of the target object is updated based on the user intent, thereby improving the accuracy and reliability of application control.

[0082] Figure 3 A flowchart of an application control method provided by an embodiment of the present disclosure.

[0083] like Figure 3 As shown, the application control method may include the following steps:

[0084] Step 301: upon receiving a first voice input by a user, recognize the first voice and determine a target intent and a target object of the first voice.

[0085] Step 302, determining a first pinyin sequence corresponding to the target object and a second pinyin sequence corresponding to each candidate object in the controlled application.

[0086] The specific implementation forms of step 301 to step 302 can refer to the detailed descriptions in other embodiments of the present disclosure, and will not be described in detail here.

[0087] Step 303, determining the first parameter according to whether the second pinyin letter at each position in the second pinyin sequence is the same as the first pinyin letter at the same position in the first pinyin sequence.

[0088] The first parameter may be the same number of the second pinyin letters and the first pinyin letters at the same position.

[0089] In the present disclosure, after determining the first Pinyin sequence corresponding to the target object and the second Pinyin sequence corresponding to each candidate object in the controlled application, the first parameter can be determined based on whether the second Pinyin letter at each position in the second Pinyin sequence is the same as the first Pinyin letter at the same position in the first Pinyin sequence, and based on the number of second Pinyin letters at the same position that are the same as the first Pinyin letters, thereby providing a data basis for determining the similarity between the first Pinyin sequence and each second Pinyin sequence.

[0090] Step 304, determining a second parameter according to the length of the pinyin letters included in the first pinyin sequence.

[0091] In the present disclosure, after determining the first parameter value, the second parameter can be determined according to the length of the pinyin letters contained in the first pinyin sequence, thereby providing a data basis for determining the similarity between the first pinyin sequence and each second pinyin sequence.

[0092] Step 305: Determine the similarity based on the ratio of the first parameter to the second parameter.

[0093] In the present disclosure, after determining the second parameter, the similarity between each second pinyin sequence and the first pinyin sequence can be determined according to the ratio of each first parameter to the second parameter, thereby improving the accuracy and reliability of determining the reference object.

[0094] Step 306: determine N candidate objects with the largest corresponding similarities as multiple reference objects, where N is an integer greater than 1.

[0095] Step 307: broadcast multiple reference objects in sequence.

[0096] Step 308: When a second voice for confirming any reference object is received, a session corresponding to any reference object in the controlled application is updated based on the target intent.

[0097] The specific implementation forms of steps 306 to 308 may refer to the detailed descriptions in other embodiments of the present disclosure, and will not be described in detail here.

[0098] In the disclosed embodiment, first, upon receiving a first voice input by a user, the first voice is recognized to determine the target intent and the target object of the first voice, and then a first pinyin sequence corresponding to the target object and a second pinyin sequence corresponding to each candidate object in the controlled application are determined, and a first parameter is determined based on whether the second pinyin letter at each position in the second pinyin sequence is the same as the first pinyin letter at the same position in the first pinyin sequence, and then a second parameter is determined based on the length of the pinyin letters included in the first pinyin sequence, and similarity is determined based on the ratio of the first parameter to the second parameter, and finally N candidate objects with the largest similarity are determined as multiple reference objects, the multiple reference objects are broadcasted in sequence, and upon receiving a second voice for confirming any reference object, the session corresponding to any reference object in the controlled application is updated based on the target intent. Therefore, after recognizing the voice input by the user and determining the user's intention and the target object, the number of pinyin letters that correspond to the target and are the same as each candidate object at the same position is determined, and the ratio of this number to the number of pinyin letters of the target object is determined as the similarity between the corresponding candidate object and the target object. The N candidate objects with the greatest similarity are determined as reference objects, and based on the user's intention, the session of the reference object confirmed by the user is updated, thereby improving the reliability and accuracy of application control.

[0099] Figure 4 A flowchart of an application control method provided by an embodiment of the present disclosure.

[0100] like Figure 4 As shown, the application control method may include the following steps:

[0101] Step 401: upon receiving a first voice input by a user, recognize the first voice and determine a target intent and a target object of the first voice.

[0102] Step 402: Based on the target object, a plurality of reference objects are obtained from the controlled application.

[0103] Step 403: broadcast multiple reference objects in sequence.

[0104] The specific implementation forms of steps 401 to 403 may refer to the detailed descriptions in other embodiments of the present disclosure, and will not be described in detail here.

[0105] Step 404: When a second voice for confirming any reference object is received and the target intention is to send a message, determine the first information to be sent.

[0106] It should be noted that the specific content of the first information can be determined according to the actual needs of the user, and this disclosure does not limit this.

[0107] Optionally, when determining the first message to be sent, if the first information is included in the first voice or the second voice, the first information can be determined based on at least one of the first voice and the second voice, which is not limited in the present disclosure.

[0108] Optionally, when determining the first message to be sent, if the first information is not included in the first voice or the second voice, the first information input indication can also be played, and the first information can be determined based on the received third voice. The present disclosure does not limit this.

[0109] The third voice may be a voice containing the first information.

[0110] In the present disclosure, when the target intention is to send a message, when the first voice or the second voice contains the first information, the first information can be directly determined; when the first voice or the second voice does not contain the first information, an information input prompt can be used to allow the user to input the first information by voice, thereby improving the convenience and flexibility of application control.

[0111] Step 405: In the controlled application, first information is sent through a session corresponding to any reference object.

[0112] In the present disclosure, after determining the first information to be sent, the first information can be sent in the controlled application through a session corresponding to any reference object to complete the user's target intention, thereby improving the convenience of the user using the application and enhancing the user experience.

[0113] It should be noted that after determining the first information to be sent, the conversation service can start the accessibility service, and send the first information through the conversation of any reference object in the controlled application, which is not limited in the present disclosure.

[0114] Among them, the barrier-free service may be a service application pre-set on the user's device, which may be used for sending and receiving information, reading messages, etc., and the present disclosure does not limit this.

[0115] It should be noted that, when the controlled application supports sending voice information, the voice information of the first information can be sent directly in the controlled application. When the controlled application does not support sending voice information, and the first information is a voice information, the conversation service can start the voice conversion service, convert the first information into text information, and then send it to any reference object in the controlled application. The present disclosure does not limit this.

[0116] In the disclosed embodiment, first, when a first voice input by a user is received, the first voice is recognized to determine the target intent and target object of the first voice, and then, based on the target object, multiple reference objects are obtained from the controlled application, and the multiple reference objects are broadcasted in sequence, and then, when a second voice for confirming any reference object is received, if the target intent is to send a message, the first information to be sent is determined, and finally, in the controlled application, the first information is sent through a session corresponding to any reference object. Thus, after determining the user intent and the target object, multiple reference objects with the highest similarity to the target object are obtained and broadcasted, and after the user confirms that any reference object is the target object, if the user intends to send a message, the information to be sent is determined, and the information is sent in the controlled application through the session of any reference object, thereby improving the convenience of application control and enhancing the user experience.

[0117] Figure 5 A flowchart of an application control method provided by an embodiment of the present disclosure.

[0118] like Figure 5 As shown, the application control method may include the following steps:

[0119] Step 501: upon receiving a first voice input by a user, recognize the first voice and determine a target intention and a target object of the first voice.

[0120] Step 502: Acquire multiple reference objects from the controlled application based on the target object.

[0121] Step 503: broadcast multiple reference objects in sequence.

[0122] The specific implementation forms of steps 501 to 503 can refer to the detailed descriptions in other embodiments of the present disclosure, and will not be described in detail here.

[0123] Step 504: When a second voice for confirming any reference object is received and the target intention is to read a message, determine the second information to be read.

[0124] It should be noted that the specific content of the second information can be determined according to the actual needs of the user, and this disclosure does not limit this.

[0125] Optionally, when determining the second information to be read, when the target intention is to read the unread session information corresponding to any reference object, the unread session information corresponding to any reference object in the controlled application can be determined as the second information, which is not limited in the present disclosure.

[0126] Optionally, when determining the second information to be read, the second information can also be obtained from a historical conversation corresponding to any reference object according to the time information and / or keywords indicated in the received voice. For example, when the received voice is "read the message sent by B on the afternoon of × year × month ×", or "read ×× sent by B", etc., the second information can be obtained from the historical conversation corresponding to B, and the present disclosure does not limit this.

[0127] In the present disclosure, when a second voice is received for confirming any reference object, when the target intention is to read the message, the unread conversation information or the historical conversation information is determined according to the user's intention to read the unread conversation information or the historical conversation information, thereby improving the comprehensiveness and reliability of reading the message.

[0128] Step 505: broadcast the second information.

[0129] In the present disclosure, after determining the second information to be read, the second information is broadcast to the user, so that the user can obtain the required information, thereby improving the reliability of application control.

[0130] It should be noted that when the second information is broadcast, the previous session information, or the next session information, etc. can be continuously broadcast through the barrier-free service according to user needs, and the present disclosure does not limit this.

[0131] Combine the following Figure 6 , an example is given to illustrate the application control method provided by the present disclosure, Figure 6 A flowchart of an application control method provided in an embodiment of the present disclosure.

[0132] like Figure 6 As shown, in the initial state, when the conversation service receives the first voice input by the user, it enters the conversation state and starts the recognition service to recognize the voice and determine the user's target intention and target object. When the user's target intention is to read the message, the accessibility service is started to enter the reading state. When the user's target intention is to send the message, the accessibility service is started to enter the sending state. When the reading state or the sending state ends, the accessibility service sends an instruction to the conversation service to indicate exiting the current state. After receiving the instruction, the conversation service can change from the conversation state to the initial state, thereby enabling users to conveniently control the application and improving the reliability of application control.

[0133] In the disclosed embodiment, when a first voice input by a user is received, the first voice is recognized to determine the target intent and target object of the first voice, and then based on the target object, multiple reference objects are obtained from the controlled application, and the multiple reference objects are broadcasted in sequence, and then when a second voice for confirming any reference object is received, if the target intent is to read a message, the second information to be read is determined, and finally the second information is broadcasted. Thus, after determining the intent and the target object, if the user's intent is to read a message, the information corresponding to any reference object confirmed as the target object is determined and broadcasted, thereby improving the reliability of application control.

[0134] In order to implement the above embodiments, the present disclosure also proposes an application control device.

[0135] Figure 7 A schematic diagram of the structure of an application control device provided in an embodiment of the present disclosure.

[0136] like Figure 7 As shown, the application control device 700 includes: an identification module 701 , an acquisition module 702 , a broadcast module 703 , and an update module 704 .

[0137] The recognition module 701 is used to recognize the first speech when receiving the first speech input by the user, and determine the target intention and target object of the first speech;

[0138] An acquisition module 702 is used to acquire multiple reference objects from the controlled application based on the target object;

[0139] A reporting module 703, used to sequentially report multiple reference objects;

[0140] The updating module 704 is used to update the conversation corresponding to any reference object in the controlled application based on the target intention when a second voice for confirming any reference object is received.

[0141] In a possible implementation of the present disclosure, the identification module 701 is further configured to:

[0142] When detecting that a preset button in the device is touched, start the voice collection service; or,

[0143] When the movement trajectory and / or frequency of the device is detected to meet the preset conditions, the voice collection service is started.

[0144] In a possible implementation of the present disclosure, the acquisition module 702 is specifically configured to:

[0145] Determine a first pinyin sequence corresponding to the target object and a second pinyin sequence corresponding to each candidate object in the controlled application;

[0146] Determining the similarity between the first pinyin sequence and each second pinyin sequence;

[0147] The N candidate objects with the largest corresponding similarities are determined as multiple reference objects, where N is an integer greater than 1.

[0148] In a possible implementation of the present disclosure, the acquisition module 702 is further configured to:

[0149] Determine the first parameter according to whether the second pinyin letter at each position in the second pinyin sequence is the same as the first pinyin letter at the same position in the first pinyin sequence;

[0150] Determine the second parameter according to the length of the pinyin letters included in the first pinyin sequence;

[0151] The similarity is determined according to the ratio of the first parameter to the second parameter.

[0152] In a possible implementation of the present disclosure, the acquisition module 702 is further configured to:

[0153] Determine the similarity between a second pinyin sequence containing the same number of pinyin letters as the first pinyin sequence and the first pinyin sequence.

[0154] In a possible implementation of the present disclosure, the updating module 704 is specifically configured to:

[0155] In the case where the target intention is to send a message, determining first information to be sent;

[0156] In the controlled application, the first information is sent through a session corresponding to any reference object.

[0157] In a possible implementation of the present disclosure, the updating module 704 is further configured to:

[0158] Determine the first information according to at least one of the first voice and the second voice; or,

[0159] The first information input indication is played, and the first information is determined according to the received third voice.

[0160] In a possible implementation of the present disclosure, the updating module 704 is specifically configured to:

[0161] In case the target intention is to read a message, determining a second information to be read;

[0162] Report the second message.

[0163] In a possible implementation of the present disclosure, the updating module 704 is further configured to:

[0164] determining the unread session information corresponding to any reference object in the controlled application as the second information; or,

[0165] According to the time information and / or keywords indicated in the received voice, the second information is acquired from a historical conversation corresponding to any reference object.

[0166] In a possible implementation of the present disclosure, the acquisition module 702 is further configured to:

[0167] Determine the controlled application based on the first voice; or,

[0168] The input indication of the controlled application is played, and the controlled application is determined according to the received fourth voice.

[0169] The functions and specific implementation principles of the above modules in the embodiments of the present disclosure can be referred to the above method embodiments, and will not be repeated here.

[0170] In the disclosed embodiment, first, when a first voice input by a user is received, the first voice is recognized to determine the target intent and target object of the first voice, and then, based on the target object, multiple reference objects are obtained from the controlled application, and the multiple reference objects are broadcasted in sequence, and then, when a second voice for confirming any reference object is received, the session corresponding to any reference object in the controlled application is updated based on the target intent. Thus, by recognizing the first voice input by the user, determining the user intent and the target object, multiple reference objects close to the target object are determined from the controlled application and broadcasted, and after receiving the voice for confirming any reference object, the session of the reference object in the controlled application is updated based on the user intent, thereby improving the convenience and reliability of application control and enhancing the user experience.

[0171] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.

[0172] Figure 8 A schematic block diagram of an example electronic device 800 that can be used to implement an embodiment of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0173] like Figure 8 As shown, the device 800 includes a computing unit 801, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 802 or a computer program loaded from a storage unit 808 into a random access memory (RAM) 803. In the RAM 803, various programs and data required for the operation of the device 800 can also be stored. The computing unit 801, the ROM 802, and the RAM 803 are connected to each other via a bus 804. An input / output (I / O) interface 805 is also connected to the bus 804.

[0174] A number of components in the device 800 are connected to the I / O interface 805, including: an input unit 806, such as a keyboard, a mouse, etc.; an output unit 807, such as various types of displays, speakers, etc.; a storage unit 808, such as a disk, an optical disk, etc.; and a communication unit 809, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 809 allows the device 800 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0175] The computing unit 801 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 801 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 801 performs the various methods and processes described above, such as the application control method. For example, in some embodiments, the application control method may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 808. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 800 via ROM 802 and / or communication unit 809. When the computer program is loaded into RAM 803 and executed by the computing unit 801, one or more steps of the application control method described above may be performed. Alternatively, in other embodiments, the computing unit 801 may be configured to perform the application control method in any other appropriate manner (e.g., by means of firmware).

[0176] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0177] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable application control device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine as a stand-alone software package and partially on a remote machine, or entirely on a remote machine or server.

[0178] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0179] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0180] The systems and techniques described herein can be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), the Internet, and a blockchain network.

[0181] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship between the client and the server is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services ("Virtual Private Server", or "VPS" for short). The server may also be a server of a distributed system, or a server combined with a blockchain.

[0182] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0183] In addition, the terms "first" and "second" are used for descriptive purposes only and cannot be understood as indicating or implying relative importance or implicitly indicating the number of indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In the description of the present disclosure, the meaning of "multiple" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined. In the description of the present disclosure, the words "if" and "if" used can be interpreted as "at the time of" or "when" or "in response to determination" or "under the circumstances of".

[0184] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. An application control method, comprising: When receiving a first voice input by a user, recognizing the first voice and determining a target intent and a target object of the first voice; Based on the target object, obtaining a plurality of reference objects from the controlled application; broadcasting the multiple reference objects in sequence; When a second voice for confirming any reference object is received, a session corresponding to any reference object in the controlled application is updated based on the target intention.

2. The method of claim 1, wherein: Before receiving the first voice input by the user, the method further includes: When detecting that a preset button in the device is touched, start the voice collection service; or, When the movement trajectory and / or frequency of the device is detected to meet the preset conditions, the voice collection service is started.

3. The method of claim 1, wherein: The acquiring a plurality of reference objects from the controlled application based on the target object includes: Determine a first pinyin sequence corresponding to the target object and a second pinyin sequence corresponding to each candidate object in the controlled application; Determining the similarity between the first pinyin sequence and each second pinyin sequence; The N candidate objects with the largest corresponding similarities are determined as the multiple reference objects, where N is an integer greater than 1.

4. The method of claim 3, wherein: Determining the similarity between the first pinyin sequence and each second pinyin sequence includes: Determine a first parameter according to whether the second pinyin letter at each position in the second pinyin sequence is the same as the first pinyin letter at the same position in the first pinyin sequence; Determining a second parameter according to the length of the pinyin letters contained in the first pinyin sequence; The similarity is determined according to a ratio of the first parameter to the second parameter.

5. The method of claim 3, wherein: The determining of the similarity between the first pinyin sequence and each second pinyin sequence comprises: Determine the similarity between a second pinyin sequence containing the same number of pinyin letters as the first pinyin sequence and the first pinyin sequence.

6. The method according to any one of claims 1 to 5, wherein: The updating of the session corresponding to any reference object in the controlled application based on the target intent includes: In the case where the target intention is to send a message, determining first information to be sent; In the controlled application, the first information is sent through a session corresponding to any one of the reference objects.

7. The method of claim 6, wherein: The determining of the first information to be sent includes: determining the first information according to at least one of the first voice and the second voice; or, The first information input indication is played, and the first information is determined according to the received third voice.

8. The method according to any one of claims 1 to 5, wherein: The updating of the session corresponding to any reference object in the controlled application based on the target intent includes: In case the target intention is to read a message, determining second information to be read; The second information is broadcasted.

9. The method of claim 8, wherein: The step of determining the second information to be read includes: determining the unread session information corresponding to any reference object in the controlled application as the second information; or, The second information is acquired from a historical conversation corresponding to any one of the reference objects according to the time information and / or keywords indicated in the received voice.

10. The method according to any one of claims 1 to 5, wherein: Before acquiring a plurality of reference objects from the controlled application based on the target object, the method further includes: Determine the controlled application based on the first voice; or, The input indication of the controlled application is played, and the controlled application is determined according to the received fourth voice.

11. An application control device, wherein: The device comprises: A recognition module, configured to recognize a first voice input by a user and determine a target intent and a target object of the first voice when the first voice is received; An acquisition module, used for acquiring a plurality of reference objects from a controlled application based on the target object; A reporting module, used for reporting the multiple reference objects in sequence; An updating module is used to update a session corresponding to any reference object in the controlled application based on the target intention when a second voice for confirming any reference object is received.

12. The device of claim 11, wherein: The identification module is further used for: When detecting that a preset button in the device is touched, start the voice collection service; or, When the movement trajectory and / or frequency of the device is detected to meet the preset conditions, the voice collection service is started.

13. The device of claim 11, wherein: The acquisition module is specifically used for: Determine a first pinyin sequence corresponding to the target object and a second pinyin sequence corresponding to each candidate object in the controlled application; Determining the similarity between the first pinyin sequence and each second pinyin sequence; The N candidate objects with the largest corresponding similarities are determined as the multiple reference objects, where N is an integer greater than 1.

14. The device of claim 13, wherein: The acquisition module is further used for: Determine a first parameter according to whether the second pinyin letter at each position in the second pinyin sequence is the same as the first pinyin letter at the same position in the first pinyin sequence; Determining a second parameter according to the length of the pinyin letters contained in the first pinyin sequence; The similarity is determined according to a ratio of the first parameter to the second parameter.

15. The device of claim 13, wherein: The acquisition module is further used for: Determine the similarity between a second pinyin sequence containing the same number of pinyin letters as the first pinyin sequence and the first pinyin sequence.

16. The device according to any one of claims 11 to 15, wherein: The update module is specifically used for: In the case where the target intention is to send a message, determining first information to be sent; In the controlled application, the first information is sent through a session corresponding to any one of the reference objects.

17. The device of claim 16, wherein: The update module is further used for: determining the first information according to at least one of the first voice and the second voice; or, The first information input indication is played, and the first information is determined according to the received third voice.

18. The device according to any one of claims 11 to 15, wherein: The update module is specifically used for: In case the target intention is to read a message, determining second information to be read; The second information is broadcasted.

19. The device of claim 18, wherein: The update module is further used for: determining the unread session information corresponding to any reference object in the controlled application as the second information; or, The second information is acquired from a historical conversation corresponding to any one of the reference objects according to the time information and / or keywords indicated in the received voice.

20. The device according to any one of claims 11 to 15, wherein: The acquisition module is further used for: Determine the controlled application based on the first voice; or, The input indication of the controlled application is played, and the controlled application is determined according to the received fourth voice.

21. An electronic device, characterized in that: include: at least one processor; and, a memory communicatively coupled to the at least one processor; The memory stores instructions that may be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method according to any one of claims 1 to 10.

22. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1-10.

23. A computer program product comprising a computer program, which, when executed by a processor, implements the method according to any one of claims 1 to 10.

Images