Intelligent recommendation method, device and system and computer readable storage medium

Abstract

The invention provides an intelligent recommendation method, device and system and a computer readable storage medium, and the method comprises the steps: responding to a condition that first electronic equipment and second electronic equipment are in a connection state, and the first electronic equipment is in a call state, and transcribing voice information in a call process into text information; analyzing and identifying entity content included in the text information; in response to the fact that the entity content contains effective entity content, generating recommendation information corresponding to the effective entity content; and sending the recommendation information to the second electronic equipment for display on the second electronic equipment. Meanwhile, an artificial intelligence model can be used for executing effective entity content recognition in the intelligent recommendation method executed by the first electronic equipment.

Description

Background Art

[0002] With the popularization of automobiles and the rapid development of science and technology, the intelligent interconnection between mobile phones and car computers has become an indispensable part of modern smart travel. The demand and usage scenarios for the interconnection between mobile phones and car computers are increasing, and users hope that car computers have richer functions. Especially with the advancement of artificial intelligence, simple car-computer interconnection can no longer meet people's needs. The deep integration of car computers and mobile phones to achieve seamless information sharing and efficient functional collaboration is an urgent need for modern people for intelligent and personalized travel.

[0003] However, in some car-connected scenarios, there are many user inconveniences. For example, while driving, a user talks to a friend and agrees to go to a certain place (for example, address a). After the call, the user needs to open the map app and enter the above address a to search and initiate navigation, and then go to the address. This operation is dangerous for drivers, because after getting the address on the phone, the driver generally needs to stop the car and type in the address information, and then re-initiate navigation to use the address information. The operation steps are cumbersome and affect driving safety.

[0004] In addition, if the driver receives a call from colleague A while driving, and colleague A asks the user to contact colleague B to confirm an urgent matter and shares colleague B's contact number, the user needs to stop the car to record the number and call colleague B. After the driver gets another phone number learned during the call, he cannot record the number in real time and needs to remember it in his mind or stop the car temporarily to record and save it, and then call the number, which affects the driver's concentration and requires more operation steps.

[0005] In other words, if other people share some valuable information through conversation while the vehicle is driving, it cannot be quickly executed during driving. The driver cannot use this information directly and needs to confirm safety before stopping the car. If the vehicle is driving on a highway, it is impossible to stop the car in a short period of time, which causes many inconveniences and affects driving safety. Summary of the invention

[0006] One of the purposes of the invention disclosed herein is to improve the user's operating convenience during vehicle driving.

[0007] According to a first aspect of the present disclosure, there is provided an intelligent recommendation method, which is applied to a first electronic device and includes: in response to the first electronic device and the second electronic device being in a connected state, and the first electronic device being in a call state, transcribing voice information during the call into text information; analyzing and identifying entity content included in the text information; in response to identifying that the entity content contains valid entity content, generating recommendation information corresponding to the valid entity content; and sending the recommendation information to the second electronic device for display on the second electronic device.

[0008] Optionally, in response to the first electronic device and the second electronic device being connected and the first electronic device being in a call state, the step of transcribing voice information during the call into text information may include: in response to the first electronic device and the second electronic device being connected and the first electronic device being in a call state, generating a call interface, and transmitting the call interface to the second electronic device for display on the second electronic device, the call interface including a call transcription option.

[0009] Optionally, in response to confirming that a call transcription option on the second electronic device is selected, voice information during the call may be transcribed into text information.

[0010] Optionally, the valid entity content may include at least one of a phone number, a schedule, music, and a location.

[0011] Optionally, the recommendation information may be displayed on the second electronic device in the form of a service card.

[0012] Optionally, there may be multiple valid entity contents, and the step of generating recommendation information corresponding to the valid entity content includes: generating multiple recommendation information corresponding to the multiple valid entity contents.

[0013] Optionally, the intelligent recommendation method may further include: in response to confirming that the service card displayed on the second electronic device is selected, enabling an application or service corresponding to the selected service card on the first electronic device for display on the second electronic device.

[0014] Optionally, enabling an application or service corresponding to a selected service card on a first electronic device for display on a second electronic device may include: in response to at least one service card among the service cards being selected, enabling an application or service corresponding to the service card, and inputting at least a portion of the information in the service card into the corresponding application or service.

[0015] Optionally, the service card may be a navigation card, and in response to confirming that the navigation card displayed on the second electronic device is selected, a navigation application corresponding to the selected navigation card is enabled on the first electronic device and navigation is started based on the address entity information contained in the navigation card.

[0016] Optionally, in response to failure to find the longitude and latitude information corresponding to the address entity in the navigation card, information including a plurality of candidate navigation addresses may be sent to the second electronic device for display on the second electronic device.

[0017] According to a second aspect of the present disclosure, there is provided an intelligent recommendation method, which is applied to a second electronic device and includes: receiving recommendation information transmitted by the intelligent recommendation method from a first electronic device.

[0018] Optionally, the intelligent recommendation method may further include: displaying a call interface including a call transcription option sent by the first electronic device on the second electronic device.

[0019] Optionally, the intelligent recommendation method may further include: displaying a service card corresponding to the recommendation information on the second electronic device.

[0020] Optionally, the intelligent recommendation method may further include: in response to at least one service card in the service cards being selected, sending information that a corresponding position of at least one service card is selected to the first electronic device.

[0021] Optionally, the intelligent recommendation method may further include: displaying an application or service corresponding to the selected service card on the second electronic device.

[0022] Optionally, in response to a navigation card displayed on the second electronic device being selected, a navigation application corresponding to the selected navigation card is enabled on the second electronic device and navigation is started based on the address entity information included in the navigation card.

[0023] Optionally, in response to failure to find the longitude and latitude information corresponding to the address entity in the navigation card, a plurality of candidate navigation addresses may be displayed on the second electronic device.

[0024] According to a third aspect of the present disclosure, an intelligent recommendation method is provided, which is applied to a third electronic device and includes: obtaining a session status of a first electronic device interconnected with the third electronic device; in response to determining that the first electronic device is in a call state, transcribing voice information during the call into text information; analyzing and identifying entity content included in the text information; in response to identifying that the entity content contains valid entity content, generating recommendation information corresponding to the valid entity content, and displaying a service card corresponding to the recommendation information based on the recommendation information.

[0025] Optionally, the intelligent recommendation method may further include: displaying a call interface including a call transcription option, and the step of transcribing the voice during the call into text information includes: in response to the call transcription option being selected, transcribing the voice information during the call into text information.

[0026] Optionally, the intelligent recommendation method may further include: in response to at least one of the service cards being selected, enabling a corresponding application or service and inputting at least a portion of the recommendation information into the corresponding application or service.

[0027] According to a fourth aspect of the present disclosure, an electronic device is provided, which includes a memory and a processor, wherein the memory stores a program or instruction, and when the program or instruction is executed by the processor, the processor is prompted to execute the above-mentioned intelligent recommendation method.

[0028] According to a fifth aspect of the present disclosure, an intelligent recommendation system is provided, the intelligent recommendation system comprising: a first electronic device, the first electronic device is the above electronic device, and a second electronic device, the second electronic device is the above electronic device.

[0029] Optionally, the first electronic device is a mobile terminal, and the second electronic device is a vehicle-mounted terminal.

[0030] According to a sixth aspect of the present disclosure, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a program or instruction, and when the program or instruction is executed by a processor, the processor is prompted to execute the above-mentioned intelligent recommendation method.

[0031] The intelligent recommendation method according to the embodiment of the present disclosure can improve the driving safety of users. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Other features, objects and advantages of the present application will become more apparent by reading the detailed description of non-limiting embodiments made with reference to the following drawings.

[0033] Figure 1 is a flow chart of an intelligent recommendation method according to a first embodiment of the present disclosure; Figure 2 is a schematic diagram showing a call transcription user interface provided by a vehicle computer during a call according to the present disclosure; Figure 3 is a schematic diagram showing a user interface for a user to transcribe using the “call transcription” of the present disclosure; Figure 4 is a schematic block diagram showing a vehicle connection solution according to an embodiment of the present disclosure; Figure 5 is a schematic diagram showing the effect of a smart service card according to the first embodiment of the present disclosure; Figure 6 is a flow chart showing navigation initiated by a navigation card based on intelligent recommendation according to the first embodiment of the present disclosure; Figure 7 is a flowchart showing steps of acquiring and processing text information according to a first embodiment of the present disclosure; Figure 8 is a flowchart illustrating entity extraction and intelligent recommendation according to the first embodiment of the present disclosure; Fig. 9 is a flow chart showing a complete vehicle-connected transcription and intelligent recommendation method according to an embodiment of the present disclosure; Fig.10 is a flow chart of an intelligent recommendation method according to a second embodiment of the present disclosure; Fig.11 A flowchart of an intelligent recommendation method according to a third embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0034] The following detailed description is provided to help gain a comprehensive understanding of the methods, devices and / or systems described herein. However, the order of operations described herein is only an example and is not limited to those orders set forth herein, but may be equivalently replaced or changed except for operations that must occur or be performed in a specific order. In addition, for greater clarity and simplicity, the description of content known in the art will be omitted or simplified.

[0035] Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as those generally understood by those skilled in the art to which the present disclosure belongs after understanding the present disclosure. Unless explicitly defined as such herein, terms (such as those defined in general dictionaries) should be interpreted as having a meaning consistent with their meaning in the context of the relevant art and the present disclosure, and should not be interpreted in an idealized or overly formal manner.

[0036] Unless otherwise specified, the same reference numerals generally refer to the same elements (e.g., components, steps, and methods). Reference numerals described in previous embodiments may be omitted if they appear again in later embodiments. In addition, the technical features described in different or the same embodiments may be combined in any manner, as long as the combined embodiments or technical solutions are complete and can solve the technical problems of the present application or achieve the technical effects described or not described in the present disclosure but can be determined based on the above complete technical solutions.

[0037] It should be noted that, in the absence of conflicts between the various embodiments, these embodiments and their features may be combined with each other.

[0038] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process and related instructions of the system described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0039] The present disclosure transcribes voice information into text information when a first electronic device (e.g., a mobile terminal) and a second electronic device (e.g., a car machine or a vehicle-mounted terminal) are interconnected, and then analyzes and identifies entities of the transcribed text information when the first electronic device is detected to be in a call state (e.g., a video call or a voice call). If valid entity content is identified, corresponding recommendation information is generated. As an example, when implemented by a first electronic device, in addition to the above steps, the above intelligent recommendation method may also include the step of sending recommendation information to the second electronic device for display on the second electronic device. When implemented by a second electronic device, the above intelligent recommendation method may also include the step of receiving recommendation information transmitted by the above intelligent recommendation method and / or displaying a service card corresponding to the recommendation information based on the recommendation information.

[0040] As an example, the corresponding application software can be enabled according to the recommendation information, or can be started according to the user's input (for example, touching a specific control interface or operation button on the screen interface, voice input, etc.). The vehicle computer here refers to the vehicle terminal, which can be equipped with a vehicle information system or entertainment platform, and the vehicle computer can be an intelligent vehicle computer or a non-intelligent vehicle computer.

[0041] As an example, steps such as voice transcription, analysis of text information and entity recognition, and generation of recommendation information may be performed by a first electronic device (e.g., a mobile terminal) or a second electronic device (e.g., a vehicle-mounted terminal). The call on the mobile terminal may be a two-party or multi-party conversation conducted through a dialing application (APP) or other APP capable of voice and / or video calls.

[0042] As an example, when it is detected that the first electronic device is in a call state, an intelligent call transcription option may be provided on the screen of the second electronic device. In response to the user starting the intelligent call transcription function (for example, clicking the intelligent call transcription option), the call content is transcribed into text information, and the transcribed text may be analyzed and entity recognized during the call and / or after the call. If a valid entity (such as an address entity or a number entity or a schedule entity, a navigation entity, etc.) is recognized, corresponding recommendation information (for example, a service card (navigation card or a phone card or a schedule card, etc.) is generated according to the action (Action) corresponding to the entity, and the service card may be displayed (for example, projected display) on the car screen. After the user selects the service card on the car, navigation or a call may be initiated on the car with one click. The technical solution of the present disclosure is described in detail below in conjunction with the accompanying drawings.

[0043] First embodiment All steps in the intelligent recommendation method of the first embodiment of the present disclosure may be executed by a first electronic device (eg, a mobile terminal such as a mobile phone).

[0044] Figure 1 is a flowchart of an intelligent recommendation method according to a first embodiment of the present disclosure, Figure 2 is a schematic diagram showing a call transcription user interface provided by a vehicle computer during a call according to the present disclosure, Figure 3 is a schematic diagram showing a user interface for a user to transcribe using the “call transcription” of the present disclosure, Figure 4 It is a schematic block diagram showing a vehicle connection solution according to an embodiment of the present disclosure.

[0045] Reference Figure 1 According to the first embodiment of the present disclosure, the intelligent recommendation method may include step S110, step S120, step S130, step S140, step S150 and step S160.

[0046] In step S110, it is determined whether the first electronic device is interconnected with the second electronic device and whether the first electronic device is in a call state.

[0047] The conversation state of the first electronic device can be obtained by using the call state monitoring API provided by operating systems such as Android or iOS. Whether there is a call can be determined by the Bluetooth connection state, or the call state of the first electronic device can be determined by calling the system interface call-state. The method of obtaining the conversation state of the first electronic device is not specifically limited. The first electronic device can be interconnected with the second electronic device (for example, wirelessly or wired). The first electronic device can detect the connection state between the first electronic device and the second electronic device through the API or SDK in the first electronic device.

[0048] For details, please refer to Figure 4 , the first electronic device (for example, a mobile terminal of a mobile phone) and the second electronic device (for example, a car computer) can be connected via USB or wirelessly (for example, via Bluetooth, WIFIP2P), and the mobile car connection application software (for example, CarLinkApp) and the car computer are interconnected through the car computer protocol (for example, ICCOA / Carlife). CarLinkApp can provide screen projection services and audio services, and interact with the car computer through the car computer protocol ICCOA / Carlife. At the same time, the first electronic device can create a virtual screen and provide CarLinkApp to the user with map, music, phone and other application services adapted to the car computer screen (such as Figure 4The launcher, calls, settings, media, etc. in the car are displayed on the virtual screen. CarLinkApp can capture the video stream of the virtual screen and send it to the car screen through the ICCOA / Carlife car connection protocol to realize screen projection. The connection method, screen projection method, and information interaction method between the first electronic device and the second electronic device are only examples, and the present disclosure is not limited thereto. For example, the first electronic device can be interconnected with the second electronic device by wire.

[0049] In step S120, in response to the first electronic device and the second electronic device being in a connected state and the first electronic device being in a call state, voice information during the call is transcribed into text information.

[0050] Reference Figure 2 and Figure 3 The car-connected application CarLinkApp in the user's mobile phone is connected to the car computer through USB or wireless means through the existing Carlife / ICCOA protocol. When the mobile phone makes a call, the call interface is displayed on the car computer screen (for example, the screen is projected). The call interface includes a "call transcription" button, such as Figure 2 As shown. The mobile phone displays the original call interface, while the difference between the car terminal and the mobile phone is that the call interface of the car terminal adds the option of "call transcription". Therefore, in response to the first electronic device and the second electronic device being connected and the first electronic device being in a call state, a call interface (including a call transcription option) can be generated, and the call interface can be transmitted to the second electronic device for display on the second electronic device. As an example, a call interface including a "call transcription" button can also be displayed on the first electronic device at the same time.

[0051] As an example, during a call, voice information can be automatically transcribed into text information. However, this is only an example, and during a call, the voice information during the call can be transcribed into text information after the user selects the "call transcription" option on the second electronic device. For example, during a call, the user can touch the "call transcription" button in the call interface on the second electronic device, and the first electronic device can respond to confirming that the "call transcription" button in the call interface on the second electronic device is selected, and transcribe the voice information during the call into text information. As an example, the second electronic device can send the coordinates input by the user by clicking on the screen of the second electronic device to the first electronic device, and the first electronic device can confirm whether the "call transcription" button in the call interface on the second electronic device is selected based on the coordinates. For example, if the coordinates are within the coordinate range corresponding to the "call transcription" button, it can be confirmed that the "call transcription" button in the call interface on the second electronic device is selected.

[0052] Reference Figure 3The user can click a "call transcription" button displayed on the second electronic device to start call transcription. During the call transcription process, the user can also click "stop transcription" to stop the call transcription. After the call ends, the transcription can be automatically stopped.

[0053] In step S130, the entity content included in the text information is analyzed and identified. The step of analyzing and identifying the entity content included in the text information may include: acquiring valid entity content through an artificial intelligence model (ie, AI model) in the first electronic device.

[0054] As an example, before the first electronic device analyzes and recognizes the text information, processing (e.g., preprocessing) may be performed on the text information. These preprocessings help improve the accuracy of subsequent entity recognition and ensure that the AI ​​model can understand and process text data more effectively. Preprocessing may include text cleaning (e.g., deleting or replacing unnecessary information of non-text characters), standardizing text (converting text to a unified format, such as all lowercase, unified abbreviation form, etc.), word segmentation (e.g., dividing continuous text into separate vocabulary units), removing pause words, etc.

[0055] The analysis and recognition of text information can be achieved through natural language processing (NLP), which aims to automatically identify and extract information fragments with specific meanings from unstructured text data. This information can be names of people, places, names of organizations, dates, times, phone numbers, addresses, etc. This information is crucial for building intelligent recommendations.

[0056] Specific methods for analyzing and identifying (or extracting) entity content may include rule-based methods, which rely on predefined rules to match and identify entities in text. Rules can include part-of-speech tagging, grammatical patterns, and other linguistic features. For example: using regular expressions to match strings in a specific format, such as phone numbers, email addresses, or postal codes. Define a vocabulary to identify common entities, such as using a list of city names to identify place names. Combine contextual clues and syntactic rules to improve recognition accuracy, such as judging whether a noun is a person's name by sentence structure. The advantages are simple implementation and good recognition effect on certain fixed-format data, but the disadvantages are poor adaptability to unforeseen formats and difficulty in handling complex semantic relationships.

[0057] Specific methods for analyzing and identifying (or extracting) entity content may also include methods based on artificial intelligence (AI), such as machine learning. For example, a small model in a vertical field, that is, an AI model trained for a specific application scenario, may be used to achieve better performance. Such models generally include, but are not limited to, the following: Transformer and its variant models: such as BERT (Bidirectional Encoder Representations from Transformers), which is a pre-trained language representation model that can effectively capture long-distance dependencies in text. This makes BERT and its variants very suitable for entity recognition tasks that require understanding of context; Self-attention mechanism: allows the model to focus on different parts of the input sequence, thereby better understanding the role of each word in the entire sentence; Bidirectional encoding: Unlike traditional unidirectional LSTM, BERT can process text from both the front and back directions at the same time, improving the ability to understand context. Combination of CRF (Conditional Random Field) and LSTM (Long Short-Term Memory Network): Although traditionally widely used in sequence labeling tasks, it may encounter computational inefficiencies when processing very long texts, or fail to fully capture long-range dependencies due to context window limitations.

[0058] Compared with rule-based methods, machine learning-based methods can respond to various changes more flexibly, and the performance of the model will gradually improve as more data is added. However, this method requires higher computing resources and professional knowledge to design, train and optimize the model.

[0059] In step S140, it is determined whether the identified content contains valid entity content (as shown in Table 1 below).

[0060] In step S150, in response to identifying that the entity content includes valid entity content, recommendation information corresponding to the valid entity content is generated. The recommendation information can be displayed on the second electronic device in the form of a service card. The valid entity content can be one or more. When there is one valid entity content, one piece of recommendation information corresponding to it is generated; when there are multiple valid entity contents, the step of generating recommendation information corresponding to the valid entity content may include: generating multiple recommendation information corresponding to multiple valid entity contents.

[0061] Once the entity is successfully extracted and / or classified, the next step is to generate corresponding intelligent recommendation information based on the type of entity. For example, if a valid address entity is detected, relevant information can be sent to the second electronic device to display a "navigate to this address" option (i.e., a service card) on the second electronic device (e.g., a car interface); if it is a phone number, an "dial this number" option (i.e., a service card) can be provided. In this way, not only can the user's operation process be simplified, but also a more personalized and intelligent service experience can be provided to the user. The specific type of intelligent recommendation based on the entity content or the pre-defined valid entity content can be shown in Table 1 below.

[0062] Table 1

[0063] Navigation: When a valid address entity is recognized in the text, a navigation card can be generated. The user can click on the card to start the navigation application and use the address as the destination. This address can be stored or displayed in the form of a normal text string. When multiple valid address entities are recognized in the text, multiple corresponding navigation cards can be generated. The user can click on any of the multiple navigation cards to start the navigation application and use the address as the destination.

[0064] Phone number: If a phone number appears in the text, a phone card can be created to allow the user to dial this number directly from the car interface. Similarly, the phone number here can also exist in the form of a string for easy processing and display. When it is recognized that the text contains multiple phone numbers, multiple corresponding call cards can be generated. The user can click on any of the multiple call cards to start the dialing APP or other voice call APP, and use the phone number as the call target. The phone number here can refer to a phone number that can be dialed through the dialing APP, or it can refer to a phone information that can be dialed through other voice call APPs (for example, a WeChat contact number). As an example, if the first electronic device recognizes through semantic understanding that Zhang San needs to be contacted, but the other party does not mention Zhang San's number, it can be matched through the contact information in the first electronic device, and finally Zhang San's phone number (which may include Zhang San's name) is generated as a service card and sent to the second electronic device for display on the second electronic device.

[0065] Date: For specific date or time information mentioned, it can be suggested to add it to the user's calendar or reminder service to help users manage time and appointments. This data can be parsed and saved in a standard date format for subsequent use in schedule management applications. Similarly, when it is recognized that the text contains multiple phone dates, multiple corresponding schedule cards can be generated. The user can choose to click on any one or more of the multiple schedule cards to start the schedule APP and create a schedule with the date as the schedule date. In addition, a schedule can be established based on the identified items corresponding to the date.

[0066] Music: When a song title or singer name is recognized in the text, a music card can be generated. The user can click on the card to start the music player. For example, the song title or singer name can be entered into the music player for search and the corresponding song can be played. For example, when multiple songs are searched, the user can select them and then play the corresponding song according to the user's selection.

[0067] However, the present disclosure is not limited to this. The present disclosure can predefine other entity contents besides the above four entity contents. For example, food information and scenic spot information can be extracted from the transcribed text information for recommendation, and food entities or scenic spot entities can be predefine accordingly.

[0068] In step S160, the recommendation information is sent to the second electronic device for display on the second electronic device.

[0069] The recommendation information may be displayed on the second electronic device in the form of a service card. The user may select at least one service card displayed on the second electronic device.

[0070] The intelligent recommendation method of the first embodiment of the present disclosure may also include: in response to confirming that the service card displayed on the second electronic device is selected, enabling an application or service corresponding to the selected service card on the first electronic device for display on the second electronic device.

[0071] As an example, the recommendation information can be transmitted to the second electronic device through the CarLinkApp in the first electronic device. However, this is only an example, and the manner of sending the recommendation information to the second electronic device in the present disclosure is not limited thereto.

[0072] In addition, the user may select at least one service card by touching the screen of the second electronic device, or by voice input, for example, the user may input a voice message for selecting at least one service card to the second electronic device to select at least one service card displayed on the second electronic device. The method for the user to select a service card is not limited thereto.

[0073] The user input here can come from the person making the call or other passengers.

[0074] Enabling an application or service corresponding to a selected service card on a first electronic device for display on a second electronic device includes: in response to confirming that at least one service card among the service cards displayed on the second electronic device is selected, enabling the application or service corresponding to the service card, and inputting at least a portion of the information in the service card into the corresponding application or service.

[0075] As an example, after the first electronic device analyzes and identifies the valid entity content, the corresponding application in the first electronic device can be enabled and at least a part of the recommended information can be input into the corresponding application or service. At the same time, the application or service displayed on the first electronic device can be projected on the second electronic device. In this process, when there are multiple valid entity contents, multiple recommendation information corresponding to multiple valid entity contents can be displayed in the form of service cards by the second electronic device. The user can select at least one of the multiple service cards displayed on the second electronic device as needed, and then enable the corresponding application or service in the first electronic device. When multiple applications or services need to be enabled, multiple selections can be made, or multiple applications or services can be enabled at the same time after a one-time selection. As an example, the valid entity content may include at least one of a phone number, a schedule, music, and a location, and the corresponding application software may be a dialing APP, a schedule APP, and a navigation APP, respectively.

[0076] Taking the service card as a navigation card as an example, in response to confirming that the navigation card displayed on the second electronic device is selected, the navigation application corresponding to the selected navigation card is enabled on the first electronic device and navigation begins based on the address entity information contained in the navigation card.

[0077] In response to failure to find the longitude and latitude information corresponding to the address entity in the navigation card, information including a plurality of candidate navigation addresses is sent to the second electronic device for display on the second electronic device.

[0078] Figure 5 is a schematic diagram showing the effect of a smart service card according to the first embodiment of the present disclosure, Figure 6 4 is a flow chart showing initiating navigation based on a navigation card with intelligent recommendation according to the first embodiment of the present disclosure.

[0079] The service card on the second electronic device may be Figure 5 As shown, for the service card displayed on the screen of the second electronic device, the user can initiate navigation or make a call with one click, etc.

[0080] As an example, in response to confirming that a navigation card corresponding to the recommended information displayed on the second electronic device is selected, a navigation application corresponding to the selected navigation card may be enabled on the first electronic device. In response to confirming that a navigation card displayed on the second electronic device is selected, a navigation application corresponding to the selected navigation card may be enabled on the first electronic device and navigation may be started based on the address entity information contained in the navigation card.

[0081] Users can also edit or modify the recommended information before starting the navigation service. For example, they can change the destination before initiating navigation, or adjust the time and location when creating an appointment.

[0082] When the user selects the address card displayed on the second electronic device, the address card contains text information of an address, such as the address text information corresponding to Luogang Wanda Plaza is: "Luogang Wanda Plaza". The above address text information "Luogang Wanda Plaza" can be input into the map app, and the longitude and latitude information of the address can be queried through the map API. If available, it means that the address can be directly navigated. However, in practice, the longitude and latitude information may not be queried due to typos or insufficient details in the address. At this time, the address POI (Point of Interest) can be queried. POI refers to a location with specific meaning or attraction. They contain detailed geographic location data and other related information, such as name, category, longitude and latitude. These data can help the system locate the destination intended by the user more accurately. Each POI contains at least basic information of name, category, longitude and latitude. After obtaining the POI list, multiple candidate addresses are prompted for the user to choose. The user selects one of the POI addresses and initiates navigation.

[0083] When the initial geocoding fails, you can use the input address text as the basis to perform a fuzzy matching search using the POI database. This will find places similar or related to the input address and list multiple candidate addresses for the user to choose from. Each candidate address is a complete POI record.

[0084] In this way, even if there is uncertainty about the original address, a range of possible destination options are still provided, increasing the probability of finding the correct location.

[0085] As an example, once a list of candidate addresses is generated, it can be displayed on the vehicle screen to allow the user to review and select the one that best meets their needs. Each candidate address can be presented to the user in an intuitive manner, which may include auxiliary information such as a brief description, pictures, and even user reviews to facilitate quick judgment.

[0086] The user can select one of the candidate addresses as the final destination. After selecting, the map API can be called again to obtain the exact latitude and longitude of the selected POI, and it can be set as the navigation target to start providing detailed route guidance. In addition, in order to further improve the user experience, the user's selection can be remembered, and the POI will be recommended first when encountering similar addresses in the future, thus realizing personalized service.

[0087] The process from the user selecting the address card to the final initiation of navigation is not only a simple information transmission and technical processing, but also a comprehensive service experience that integrates intelligent recommendation and user interaction. In this way, the present disclosure can not only solve many inconveniences in traditional navigation settings, but also provide users with a more convenient and intelligent selection method to ensure that they can reach their destination safely and efficiently during driving. The following is a detailed description using address information as an example of recommended information.

[0088] The process after the user selects the address card on the second electronic device can be as follows Figure 6 shown.

[0089] Reference Figure 6 According to an embodiment of the present disclosure, the steps of enabling the map APP and inputting relevant information thereto may include step S610, step S620, step S630, step S640, step S650, step S660 and step S670.

[0090] In step S610, address information is obtained. For example, the address information in the voice call can be obtained in the manner described above.

[0091] In step S620, the longitude and latitude are queried.

[0092] In step S630, it is determined whether there are valid longitude and latitude. If not, step S640 is executed; if yes, step S670 is executed.

[0093] In step S640, POI (point of interest) is searched. When the initial geocoding fails, a fuzzy matching search can be performed using the POI database based on the input address text.

[0094] In step S650, a POI list is obtained. Places similar or related to the input address can be found, and multiple candidate addresses are listed for the user to choose. Each candidate address is a complete POI record. In this way, even if there is uncertainty in the original address, a series of possible destination options can be provided, increasing the probability of finding the correct location.

[0095] In step S660, an address in the POI is selected. As an example, once the candidate address list is generated, it can be displayed on the mobile phone screen to allow the user to view and select the one that best meets their needs. The navigation APP displayed on the mobile phone screen can be displayed on the vehicle screen at the same time, and the user can select the address list that best meets their needs on the vehicle screen and initiate navigation.

[0096] In step S670, navigation is initiated, and the navigation result is displayed (eg, projected) on the vehicle computer screen. As an example, the POI list can be displayed on the vehicle computer, and navigation can also be directly initiated through the vehicle computer.

[0097] In addition to the navigation service card, the first electronic device can also send a phone service card, a music service card, a schedule service card, etc. to the second electronic device. The specific type of the service card is not specifically limited, and different valid entities can be pre-defined according to the content or specific application scenarios that may appear in the daily call process or in the transcribed text information. The voice of the other party in the call can be recorded by the second electronic device or the first electronic device, and the voice of the other party can be recorded by the first electronic device.

[0098] Figure 7 is a flowchart showing steps of acquiring and processing text information according to the first embodiment of the present disclosure, Figure 8 is a flowchart showing entity extraction and intelligent recommendation according to the first embodiment of the present disclosure, Fig. 9 is a flow chart showing a complete vehicle-connected transcription and intelligent recommendation method according to an embodiment of the present disclosure.

[0099] like Figure 7 As shown, the car computer can be interconnected with the CarLinkAPP in the mobile phone through car computer interconnection protocols such as Carlife / ICCOA.

[0100] Specifically, the intelligent recommendation method according to an embodiment of the present disclosure may include step S710, step S720, step S730, step S740 and step S750.

[0101] In step S710, the other party's audio is recorded via the system recording module in the mobile phone.

[0102] In step S720, the user's own audio is recorded through the microphone in the vehicle computer.

[0103] In step S730, the audio stream of the user is transmitted from the vehicle to the transcription engine (STT engine) in the mobile phone, and the audio stream of the other party is input into the transcription engine and transcribed into text information. Therefore, the audio of both parties can be transcribed by the transcription engine in the mobile phone.

[0104] In step S740, the text information is processed, and the processing here may include the preprocessing described above. However, the present disclosure is not limited thereto.

[0105] In step S750, the processed text information is saved.

[0106] In other words, the audio of the user and the audio of the other party can be recorded separately and both can be transcribed by the transcription engine in the mobile phone. However, this is only an example, and the audio of the user can be recorded by the system recording module in the mobile phone, transcribed into text information, processed, and then saved, for example, to a note APP (e.g., a note APP in the mobile phone).

[0107] Specifically, after the user selects "Call Transcription" on the vehicle computer (such as Figure 3 As shown), the Android system provides the ability to distinguish audio sources. For example, when recording audio, Android MediaRecorder can set different audio sources so that uplink and downlink audio can be distinguished when obtaining the call audio stream. The call audio on the car computer uses uplink audio (VOICE_UPLINK, the audio of the caller, obtained by the microphone of the car computer) and downlink audio (VOICE_DOWNLINK, the audio of the other party in the call) to distinguish the role. Two MediaRecorder instances can be set, one is set to VOICE_UPLINK and the other is set to VOICE_DOWNLINK, so as to achieve separate recording of the voices of both parties, and transmit the recorded audio stream to the STT engine on the mobile phone in real time for transcription. During STT transcription, the two audio streams can also be transcribed separately through two different STT instances, so as to distinguish the roles of the conversation. The recognized text is sorted on the mobile phone CarLinkApp, and a complete two-way conversation text including the roles is formed according to the time and source of the transcription text. After the call, CarLinkApp can send the transcription text to the mobile phone note APP.

[0108] The above-mentioned call transcription can be performed during the call or after the call ends. In addition, after the call ends, the mobile phone extracts valuable entity data from the transcribed text (for example, providing a quick call service for the phone entity and a navigation service for the address entity), and then displays the recommended service card on the car screen, and the user selects the service card to initiate quick navigation or initiate a call.

[0109] As an example, after obtaining the transcribed text of the call content, the mobile phone can extract entity information such as the call and address through the AI ​​model (for example, NLP) in the mobile phone; different actions are generated according to the different entity types obtained, and different recommended service cards are displayed for users to choose from. For example, the action corresponding to the phone number entity is to make a call, and the action corresponding to the address entity is navigation. The first electronic device generates corresponding cards according to different actions and displays them on the screen of the second electronic device.

[0110] For details, please refer to Figure 8 According to the first embodiment of the present disclosure, the intelligent recommendation method may include step S810, step S820, step S830, step S840 and step S850.

[0111] In step S810, text transcription is performed through the mobile phone, and the voice of both parties can be transcribed through the mobile phone.

[0112] In step S820, entity extraction is performed by the mobile phone, for example, effective entity content can be extracted by an artificial intelligence (AI) model (e.g., NLP) in the mobile phone. As an example, what is effective entity content can be determined in a predefined manner. As described above, the effective entity content may include at least one of a phone number, a schedule, music, and a location.

[0113] In step S830, the valid entity content is classified by the mobile phone. For example, the valid entity content can be classified into schedule entity, phone entity, address entity and other entities.

[0114] In step S840, corresponding recommendation information is generated by the mobile phone, for example, recommendation information of schedule, calling phone, navigation and other actions.

[0115] In step S850, the recommendation information is sent to the vehicle computer connected to the mobile phone and displayed on the vehicle computer screen. After the recommendation information is displayed on the vehicle computer screen connected to the mobile phone, the user can perform various operations to utilize these intelligent recommendation services. As an example, the user can view the recommendation content, for example, the vehicle computer screen can display a series of service cards generated based on the valid entities recognized in the call transcription text.

[0116] Each card corresponds to a specific action, such as navigation, making a call, or creating a schedule. Users can scroll through different service cards through the touch screen or the car's directional control buttons and select the options they are interested in. If the navigation card corresponding to the address entity is selected, after selection, the built-in map application of the car can be automatically called, and the address can be set as the target location to start navigation. For unclear addresses, multiple candidate locations can be provided for users to choose the most suitable one. For phone number entities, users can select a phone card to dial the number directly. In addition, if there is a matching record in the contact database, the contact's name can be displayed instead of a simple number to increase user convenience. When the user selects the schedule card of the date entity, the calendar application can be opened, allowing the user to add a new event and fill in more details, such as time, notes, and other information.

[0117] As an example, before the user takes any further action, the user can be asked to confirm their choice. This ensures that the user does not make a mistake and has enough time to consider whether to proceed. Similarly, the user can cancel the action at any time.

[0118] Reference Fig. 9 According to an embodiment of the present disclosure, the intelligent recommendation method may include steps S901, S902, S903, S904, S905, S906, S907, S908, S909, S910, S911, S912, S913, S914, S915, S916, S917 and S918.

[0119] In step S901, the user's own audio is recorded through the microphone of the vehicle computer.

[0120] In step S902, the other party's audio is recorded by the system recording module of the mobile phone.

[0121] In step S903, the audio of the call of the party and the audio of the call of the other party are obtained from the vehicle through the vehicle connection APP (for example, CarLinkApp). As an example, all audio information in the call can be obtained through the vehicle connection protocol such as CarLife or ICCOA to provide a data basis for subsequent processing.

[0122] In step S904, the acquired call audio information or voice information may be converted into text information. This step may be implemented using speech recognition technology, which may convert the voice information in the call into a readable text form. The STT engine may analyze the audio stream, identify the words and sentences therein, and generate the corresponding text content. A highly accurate speech recognition algorithm may be used to ensure that the converted text is accurate.

[0123] In step S905, text content may be obtained.

[0124] In step S906: the transcribed text content is processed. The specific processing process can be as described above and will not be repeated here.

[0125] In step S907, the processed text content may be saved to a note APP in the mobile phone.

[0126] In step S908, valid entity information or entity content may be extracted from the processed text content. These entities may include addresses, phone numbers, music, dates, etc. As described above, key information in the text may be identified using natural language processing (NLP) technology and classified into different entity types.

[0127] In step S909, corresponding smart service cards, such as navigation cards, phone cards and other related cards, are generated according to these entities.

[0128] In step S914, if the selected service card is a calling card, a call can be initiated.

[0129] In step S910, if the selected card is a navigation card, the longitude and latitude can be queried. For example, the longitude and latitude information of the address entity can be queried through the map API. If the address information is clear and standard, the system can directly obtain the longitude and latitude, indicating that the address can be directly used for navigation.

[0130] In step S911, if the longitude and latitude are invalid, the POI list is queried. If the initial longitude and latitude query fails, a POI search may be initiated.

[0131] In step S912, nearby POIs may be fuzzy matched based on the address text, and a candidate address list may be generated. Each POI contains at least basic information of name, category, longitude and latitude.

[0132] In step S913, if the longitude and latitude are valid, navigation is initiated. As an example, the user can also select the correct address from the candidate list, perform a longitude and latitude query, and then initiate navigation.

[0133] As an example, navigation is initiated based on the address selected by the user. This step may include calling a map application, setting the destination, and starting to provide detailed route guidance. Although not shown, real-time traffic information and voice prompts may also be provided during navigation to ensure that the user can reach the destination safely and efficiently.

[0134] In step S915: if the user selects a service card corresponding to other actions, other actions may be performed.

[0135] In step S916, all applications or services executed on the mobile phone can be displayed through the vehicle computer. All generated service cards and navigation information can be displayed on the vehicle computer screen. Users can browse and select these cards through the touch screen or the control buttons on the steering wheel to perform corresponding operations. This design ensures that users can use these intelligent recommendation services conveniently and quickly while driving.

[0136] In step S917, the audio of both parties during the call may be merged.

[0137] In step S918, the merged audio can be saved. The user can review the conversation after the call ends, or save it as an important record. The saved audio file can be stored on the mobile phone or uploaded to the cloud for easy access at any time.

[0138] Second embodiment The steps of the intelligent recommendation method according to the second embodiment of the present disclosure may be performed by a second electronic device. The second electronic device may be, for example, a vehicle-mounted terminal or a vehicle computer, and the vehicle computer may be a non-intelligent vehicle computer. The recommendation information may be displayed by the second electronic device, and the service card may be selected by the second electronic device.

[0139] Fig.10 is a flowchart of an intelligent recommendation method according to a second embodiment of the present disclosure.

[0140] Reference Fig.10 According to the second embodiment of the present disclosure, the intelligent recommendation method may include step S1010.

[0141] In step S1010, the recommendation information is received from the first electronic device.

[0142] The recommendation information sent by the first electronic device can be displayed by means of screen projection. In addition, various applications or services running on the first electronic device can also be displayed on the second electronic device by means of screen projection.

[0143] In addition, the intelligent recommendation method according to the second embodiment of the present disclosure may further include step S1020: displaying the call interface including the call transcription option sent by the first electronic device on the second electronic device; step S1030: displaying the service card corresponding to the recommended information on the second electronic device. The manner of displaying the call interface including the call transcription option and the service card on the second electronic device has been described in the process of describing the first embodiment, and will not be repeated here.

[0144] As an example, the intelligent recommendation method according to the second embodiment of the present disclosure may also include step S1030, in which, in response to at least one service card among the service cards displayed on the second electronic device being selected, information that the corresponding position of at least one service card is selected may be sent to the first electronic device. For example, the information here may be the location information (e.g., coordinate information) touched by the user, and the second electronic device may send the coordinates input by the user clicking on the screen of the second electronic device to the first electronic device, and then the first electronic device completes the subsequent operations (e.g., enabling the corresponding service APP, etc.) through the click event distribution mechanism of Android.

[0145] As an example, the intelligent recommendation method according to the second embodiment of the present disclosure may further include: displaying the application or service corresponding to the selected service card on the second electronic device. As described above, the application or service running in the first electronic device may be displayed on the second electronic device by means of screen projection display.

[0146] Third embodiment The third embodiment of the present disclosure can be performed by a third electronic device, where the third electronic device can be a vehicle-mounted terminal or a vehicle computer. The main difference between the third electronic device and the second electronic device is the ability to analyze and process data. The second electronic device does not have a strong ability to analyze and identify valid entity content. The third electronic device can be an intelligent vehicle computer, and the second electronic device can be a non-intelligent vehicle computer. The steps of analyzing and identifying valid entity content that can be performed by the first electronic device (for example, a mobile phone) as described above, and the steps of displaying recommended information and applications or services that can be performed by the second electronic device (for example, a vehicle computer) can both be performed by the third electronic device.

[0147] Fig.11 A flowchart of an intelligent recommendation method according to a third embodiment of the present disclosure is shown.

[0148] Reference Fig.11 According to the third embodiment of the present disclosure, the intelligent recommendation method may include step S1110, step S1120, step S1130 and step S1140. In addition, according to the third embodiment of the present disclosure, the intelligent recommendation method may further include step S1150.

[0149] In step S1110, a session state of a first electronic device interconnected with a third electronic device is acquired.

[0150] The third electronic device can obtain the session status of the first electronic device. As an example, it can determine whether a call is in progress through the Bluetooth connection status. The method of obtaining the session status of the first electronic device is not specifically limited.

[0151] In step S1120, in response to determining that the first electronic device is in a call state, the voice information during the call is transcribed into text information. As an example, the voice information during the call can be transcribed into text information in real time, or after the call ends.

[0152] In step S1130 , entity content included in the text information is analyzed and recognized.

[0153] The manner in which the third electronic device analyzes and identifies the entity content included in the text information may be the same as the manner in which the first electronic device analyzes and identifies the entity content included in the text information, and will not be described in detail here.

[0154] In step S1140, in response to identifying that the entity content includes valid entity content, recommendation information corresponding to the valid entity content is generated, and a service card corresponding to the recommendation information is displayed according to the recommendation information. The specific methods of generating recommendation information and displaying recommended service cards can be as described above and will not be repeated here.

[0155] In step S1150 , in response to at least one of the service cards being selected, a corresponding application or service is enabled and at least a portion of the recommendation information is input into the corresponding application or service.

[0156] The applications or services here can all be installed on the third electronic device. That is, when the user selects a service card on the third electronic device, the corresponding application or service installed in the third electronic device can be enabled and at least part of the recommended information can be input into the corresponding application or service.

[0157] For example, when the user selects a navigation card on the third electronic device, a navigation application corresponding to the selected navigation card is enabled on the third electronic device and navigation is directly started based on the address entity information included in the navigation card.

[0158] When the longitude and latitude information corresponding to the address entity in the navigation card cannot be found, the third electronic device displays information including multiple candidate navigation addresses, and the user can further select one of the multiple candidate navigation addresses and initiate navigation.

[0159] As an example, the intelligent recommendation method according to the third embodiment of the present disclosure may further include: displaying a call interface including a call transcription option. The step of transcribing the voice during the call into text information may include: in response to the call transcription option being selected, transcribing the voice information during the call into text information.

[0160] The method of selecting the call transcription option is not specifically limited, and the user can select the call transcription by touching the call transcription option, or can select the call transcription by voice. For example, the user can input voice such as "start call transcription" or "call transcription" to transcribe the call.

[0161] Similarly, the user can also select one of the multiple candidate navigation addresses by voice and initiate navigation. For example, the user can voice input a number corresponding to one of the multiple candidate navigation addresses, and then automatically initiate navigation.

[0162] As an example, the present disclosure may also provide an intelligent recommendation system. The intelligent recommendation system may include a first electronic device and a second electronic device. The first electronic device may be a mobile terminal, and the second electronic device may be a vehicle-mounted terminal or a vehicle computer. The mobile terminal may execute the above steps that may be executed by the mobile terminal, and the vehicle-mounted terminal may execute the above steps that may be executed by the vehicle-mounted terminal.

[0163] The above has been referred to Figures 1 to 11 An intelligent recommendation method according to an exemplary embodiment of the present disclosure is described. However, it should be understood that the steps, units, modules, and systems shown in the accompanying drawings may be configured as software, hardware, firmware, or any combination of the above items to perform specific functions. For example, these systems and devices may correspond to dedicated integrated circuits, pure software codes, or modules that combine software and hardware. In addition, one or more functions implemented by these systems or devices may also be uniformly performed by components in physical entity devices (e.g., processors, clients, or servers, etc.).

[0164] As an example, the speech during a call and the voice instructions input by the user can use an automatic speech recognition (ASR) model to convert the speech part into computer-readable text. The user's speech intention can be obtained by interpreting the converted text using a natural language understanding (NLU) model. The ASR model or the NLU model can be an artificial intelligence model. The artificial intelligence model can be processed by an artificial intelligence dedicated processor designed with a hardware structure specified for artificial intelligence model processing. The artificial intelligence model can be obtained through training. Here, "obtained through training" means training a basic artificial intelligence model with multiple training data through a training algorithm to obtain a predefined operation rule or artificial intelligence model, which is configured to perform the required features (or purposes).

[0165] As an example, an artificial intelligence model may include multiple neural network layers. Each of the multiple neural network layers includes multiple weight values, and the neural network calculation is performed by calculating between the calculation result of the previous layer and the multiple weight values. Language understanding is a technology for identifying and applying / processing human language / text, including, for example, natural language processing, machine translation, dialogue systems, question answering, or speech recognition / synthesis. Examples of neural networks include, but are not limited to, convolutional neural networks (CNNs), deep neural networks (DNNs), recurrent neural networks (RNNs), restricted Boltzmann machines (RBMs), deep belief networks (DBNs), bidirectional recursive deep neural networks (BRDNNs), generative adversarial networks (GANs), and deep Q networks.

[0166] In addition, at least one of the multiple modules can be implemented by an AI model. Functions associated with AI can be executed by a non-volatile memory, a volatile memory, and a processor.

[0167] The processor may include one or more processors. In this case, the one or more processors may be general-purpose processors, such as a central processing unit (CPU), an application processor (AP), etc., a processor used only for graphics (such as a graphics processing unit (GPU), a visual processing unit (VPU) and / or an AI-specific processor (such as a neural processing unit (NPU)).

[0168] According to an embodiment of the present disclosure, a computer-readable storage medium may store a program or an instruction, which, when executed by a processor, prompts the processor to execute the above-mentioned intelligent recommendation method.

[0169] According to an embodiment of the present disclosure, a computing device may include a memory and a processor, wherein the memory stores a program or an instruction, and when the program or the instruction is executed by the processor, the processor is prompted to execute the above-mentioned intelligent recommendation method.

[0170] The intelligent recommendation system according to an embodiment of the present disclosure may include the first electronic device (eg, a mobile terminal) and the second electronic device (eg, a vehicle-mounted terminal) as described above.

[0171] The instructions stored in the computer-readable storage medium can be executed in an environment deployed in a computer device such as a client, a host, an agent device, a server, etc. It should be noted that the instructions can also be used to perform additional steps in addition to the above steps or perform more specific processing when performing the above steps. The contents of these additional steps and further processing have been described in detail in reference to Figures 1 to 11 It is mentioned in the description of related systems and methods, so it will not be repeated here to avoid repetition.

[0172] On the other hand, when the systems, units or modules shown in the drawings are implemented in software, firmware, middleware or microcode, the program code or code segments for performing the corresponding operations may be stored in a computer-readable medium such as a storage medium, so that at least one processor or at least one computing device may perform the corresponding operations by reading and running the corresponding program code or code segments. In addition, the computer-readable medium or storage medium may cause the processor to execute the intelligent recommendation method when the computer program is executed by the processor.

[0173] Examples of computer-readable storage media include read-only memory (ROM), random-access programmable read-only memory (PROM), electrically erasable programmable read-only memory (EEPROM), random-access memory (RAM), dynamic random-access memory (DRAM), static random-access memory (SRAM), flash memory, nonvolatile memory, and the like.

[0174] The intelligent recommendation method according to the embodiment of the present disclosure can improve driving safety. For example, the driver can process the information shared on the phone, such as address, phone number, etc., without distracting attention, which avoids the need to manually input information during driving, thereby reducing the risk of distracted driving.

[0175] The intelligent recommendation method according to the embodiment of the present disclosure can improve the convenience of operation. For example, the driver only needs to select the relevant card to initiate navigation or make a call with one click, which simplifies the operation steps.

[0176] It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. An intelligent recommendation method, characterized in that: The intelligent recommendation method is applied to a first electronic device and includes: In response to the first electronic device and the second electronic device being in a connected state, and the first electronic device being in a call state, transcribing voice information during the call into text information; Analyze and identify entity content included in the text information; In response to identifying that the entity content includes valid entity content, generating recommendation information corresponding to the valid entity content; The recommendation information is sent to the second electronic device for display on the second electronic device.

2. The intelligent recommendation method according to claim 1, characterized in that: In response to the first electronic device and the second electronic device being in a connected state, and the first electronic device being in a call state, the step of transcribing voice information during the call into text information includes: In response to the first electronic device and the second electronic device being in a connected state and the first electronic device being in a call state, a call interface is generated and transmitted to the second electronic device for display on the second electronic device, wherein the call interface includes a call transcription option.

3. The intelligent recommendation method according to claim 2, characterized in that: In response to confirming that the call transcription option on the second electronic device is selected, the voice information during the call is transcribed into text information.

4. The intelligent recommendation method according to any one of claims 1 to 3, characterized in that: The valid entity content includes at least one of a phone number, a schedule, music, and a location.

5. The intelligent recommendation method according to claim 1, characterized in that: The recommendation information is displayed on the second electronic device in the form of a service card.

6. The intelligent recommendation method according to claim 1, characterized in that: There are multiple valid entity contents, and the step of generating recommendation information corresponding to the valid entity contents includes: generating multiple recommendation information corresponding to the multiple valid entity contents.

7. The intelligent recommendation method according to claim 5, characterized in that: The intelligent recommendation method also includes: in response to confirming that the service card displayed on the second electronic device is selected, enabling an application or service corresponding to the selected service card on the first electronic device for display on the second electronic device.

8. The intelligent recommendation method according to claim 7, characterized in that: Enabling an application or service corresponding to the selected service card on the first electronic device for display on the second electronic device includes: In response to at least one of the service cards being selected, an application or service corresponding to the service card is enabled, and at least a portion of the information in the service card is input into the corresponding application or service.

9. The intelligent recommendation method according to claim 8, characterized in that: The service card is a navigation card. In response to confirming that the navigation card displayed on the second electronic device is selected, a navigation application corresponding to the selected navigation card is enabled on the first electronic device and navigation is started based on the address entity information contained in the navigation card.

10. The intelligent recommendation method according to claim 9, characterized in that: In response to failure to find the longitude and latitude information corresponding to the address entity in the navigation card, information including a plurality of candidate navigation addresses is sent to the second electronic device for display on the second electronic device.

11. An intelligent recommendation method, characterized in that: The intelligent recommendation method is applied to a second electronic device and comprises: receiving recommendation information transmitted by the intelligent recommendation method according to any one of claims 1 to 10 from a first electronic device.

12. The intelligent recommendation method according to claim 11, characterized in that: The intelligent recommendation method also includes: displaying a call interface including a call transcription option sent by the first electronic device on the second electronic device.

13. The intelligent recommendation method according to claim 12, characterized in that: The intelligent recommendation method further includes: displaying a service card corresponding to the recommendation information on a second electronic device.

14. The intelligent recommendation method according to claim 13, characterized in that: The intelligent recommendation method further includes: in response to at least one service card among the service cards being selected, sending information that a corresponding position of the at least one service card is selected to the first electronic device.

15. The intelligent recommendation method according to claim 14, characterized in that: The intelligent recommendation method further includes: displaying an application or service corresponding to the selected service card on the second electronic device.

16. The intelligent recommendation method according to claim 15, characterized in that: The service card is a navigation card. In response to the navigation card displayed on the second electronic device being selected, a navigation application corresponding to the selected navigation card is enabled on the second electronic device and navigation is started based on the address entity information contained in the navigation card.

17. The intelligent recommendation method according to claim 16, characterized in that: In response to failure to find the longitude and latitude information corresponding to the address entity in the navigation card, a plurality of candidate navigation addresses are displayed on the second electronic device.

18. An intelligent recommendation method, characterized in that: The intelligent recommendation method is applied to a third electronic device and includes: Acquire a session state of a first electronic device interconnected with the third electronic device; In response to determining that the first electronic device is in a call state, transcribing voice information during the call into text information; Analyze and identify entity content included in the text information; In response to identifying that the entity content includes valid entity content, recommendation information corresponding to the valid entity content is generated, and a service card corresponding to the recommendation information is displayed according to the recommendation information.

19. The intelligent recommendation method according to claim 18, characterized in that: The intelligent recommendation method further includes: displaying a call interface including a call transcription option, The step of transcribing the voice during the call into text information includes: in response to the call transcription option being selected, transcribing the voice information during the call into text information.

20. The intelligent recommendation method according to claim 18, characterized in that: The intelligent recommendation method further includes: In response to at least one of the service cards being selected, a corresponding application or service is enabled and at least a portion of the recommendation information is input into the corresponding application or service.

21. An electronic device, characterized in that: It comprises a memory and a processor, wherein the memory stores a program or an instruction, and when the program or the instruction is executed by the processor, the processor is prompted to execute the intelligent recommendation method according to any one of claims 1 to 110.

22. An electronic device, characterized in that: The invention comprises a memory and a processor, wherein the memory stores a program or an instruction, and when the program or the instruction is executed by the processor, the processor is prompted to execute the intelligent recommendation method according to any one of claims 11 to 17.

23. An intelligent recommendation system, characterized in that: The intelligent recommendation system comprises: a first electronic device, wherein the first electronic device is the electronic device according to claim 21, A second electronic device, wherein the second electronic device is the electronic device according to claim 22.

24. The intelligent recommendation system according to claim 23, characterized in that: The first electronic device is a mobile terminal, and the second electronic device is a vehicle-mounted terminal.

25. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a program or an instruction, which, when executed by a processor, causes the processor to execute the intelligent recommendation method according to any one of claims 1 to 20.

26. An electronic device, characterized in that: The invention comprises a memory and a processor, wherein the memory stores a program or an instruction, and when the program or the instruction is executed by the processor, the processor is prompted to execute the intelligent recommendation method according to any one of claims 18 to 20.

Images