Content recommendation method, device, equipment, medium and product

Abstract

The present disclosure provides a content recommendation method and device, equipment, medium and product, which relate to the fields of smart cockpit and Internet of Vehicles, and in particular to the fields of smart recommendation and content processing technology. The specific implementation scheme includes: identifying the in-vehicle scene data to obtain the state characteristic information of the in-vehicle occupants, the in-vehicle scene data including the in-vehicle scene image and / or the in-vehicle scene audio; determining the target content type to be recommended according to the state characteristic information of the in-vehicle occupants; and recommending content associated with the target content type to the in-vehicle terminal.

Description

Technical Field

[0001] The present disclosure relates to the field of artificial intelligence, and in particular to the field of intelligent recommendation and content processing technology, and can be applied to content recommendation in vehicle-mounted scenarios. Background Art

[0002] As information overload becomes increasingly prominent, content recommendation can effectively meet users' diverse content consumption needs and reduce the search cost and difficulty of users to obtain content. Content recommendation has a wide range of applications in vehicle scenarios, but in some scenarios, there are problems such as poor content matching and poor recommendation effects. Summary of the invention

[0003] The present disclosure provides a content recommendation method, device, equipment, medium and product.

[0004] According to one aspect of the present disclosure, a content recommendation method is provided, comprising: identifying in-vehicle scene data to obtain status characteristic information of in-vehicle occupants, wherein the in-vehicle scene data includes in-vehicle scene images and / or in-vehicle scene audio; determining a target content type to be recommended based on the status characteristic information of the in-vehicle occupants; and recommending content associated with the target content type to a vehicle-mounted terminal.

[0005] According to another aspect of the present disclosure, a content recommendation device is provided, comprising: a first processing module, used to identify in-vehicle scene data to obtain status characteristic information of in-vehicle occupants, wherein the in-vehicle scene data includes in-vehicle scene images and / or in-vehicle scene audio; a second processing module, used to determine a target content type to be recommended based on the status characteristic information of the in-vehicle occupants; and a third processing module, used to recommend content associated with the target content type to a vehicle-mounted terminal.

[0006] According to another aspect of the present disclosure, an electronic device is provided, comprising: at least one processor and a memory in communication with the at least one processor, wherein the memory stores instructions executable 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 perform the above-mentioned content recommendation method.

[0007] According to another aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable the computer to execute the above-mentioned content recommendation method.

[0008] According to another aspect of the present disclosure, a computer program product is provided, including a computer program, wherein the computer program implements the above-mentioned content recommendation method when executed by a processor.

[0009] 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

[0010] The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure.

[0011] Figure 1 The system architecture of the content recommendation method and device according to an embodiment of the present disclosure is schematically shown;

[0012] Figure 2 A flowchart of a content recommendation method according to an embodiment of the present disclosure is schematically shown;

[0013] Figure 3 A schematic diagram schematically shows a content recommendation method according to another embodiment of the present disclosure;

[0014] Figure 4 A schematic diagram schematically shows a content recommendation process according to an embodiment of the present disclosure;

[0015] Figure 5 A block diagram of a content recommendation device according to an embodiment of the present disclosure is schematically shown;

[0016] Figure 6 A block diagram of an electronic device for performing content recommendation according to an embodiment of the present disclosure is schematically shown. DETAILED DESCRIPTION

[0017] 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.

[0018] The terms used herein are only for describing specific embodiments and are not intended to limit the present disclosure. The terms "include", "comprising", etc. used herein indicate the existence of the features, steps, operations and / or components, but do not exclude the existence or addition of one or more other features, steps, operations or components.

[0019] All terms (including technical and scientific terms) used herein have the meanings commonly understood by those skilled in the art, unless otherwise defined. It should be noted that the terms used herein should be interpreted as having a meaning consistent with the context of this specification, and should not be interpreted in an idealized or overly rigid manner.

[0020] When using expressions such as "at least one of A, B, and C, etc.", they should generally be interpreted according to the meaning of the expression commonly understood by those skilled in the art (for example, "a system having at least one of A, B, and C" should include but is not limited to a system having A alone, B alone, C alone, A and B, A and C, B and C, and / or A, B, C, etc.).

[0021] The embodiment of the present disclosure provides a content recommendation method. The content recommendation method includes: identifying in-vehicle scene data to obtain status feature information of in-vehicle occupants, wherein the in-vehicle scene data includes in-vehicle scene images and / or in-vehicle scene audio. According to the status feature information of the in-vehicle occupants, determining the target content type to be recommended, and recommending content associated with the target content type to the in-vehicle terminal.

[0022] Figure 1 The system architecture of the content recommendation method and device according to an embodiment of the present disclosure is schematically shown. It should be noted that: Figure 1 What is shown is merely an example of a system architecture to which the embodiments of the present disclosure can be applied, in order to help those skilled in the art understand the technical content of the present disclosure, but it does not mean that the embodiments of the present disclosure cannot be used in other devices, systems, environments or scenarios.

[0023] The system architecture 100 according to this embodiment may include a data acquisition terminal 101, a vehicle terminal 102, a network 103 and a server 104. The network 103 is used to provide a medium for a communication link between the data acquisition terminal 101, the vehicle terminal 102 and the server 104. The network 103 may include various connection types, such as wired or wireless communication links or optical fiber cables, etc. The server 104 may be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud computing, network services, and middleware services.

[0024] The data acquisition terminal 101 and the vehicle-mounted terminal 102 interact with the server 104 via the network 103 to receive or send data, etc. The data acquisition terminal 101 can be used to collect in-vehicle scene data, and the data acquisition terminal 101 can include, for example, an in-vehicle camera, a vehicle-mounted sensor, etc. The vehicle-mounted terminal 102 can be a multimedia data file playback device in the vehicle.

[0025] The server 104 may be a server that provides various services, for example, it may be a background processing server (only an example) that recognizes the data sent by the data acquisition terminal 101. The background processing server may recognize and process the received image, video, audio and other data.

[0026] For example, the server 104 receives the in-vehicle scene data from the data collection terminal 101. The server 104 is used to identify the in-vehicle scene data and obtain the status characteristic information of the in-vehicle occupants. The in-vehicle scene data includes in-vehicle scene images and / or in-vehicle scene audio. The server 104 is also used to determine the target content type to be recommended based on the status characteristic information of the in-vehicle occupants, and recommend content associated with the target content type to the in-vehicle terminal 103.

[0027] It should be noted that the content recommendation method provided in the embodiment of the present disclosure can be executed by the server 104. Accordingly, the content recommendation device provided in the embodiment of the present disclosure can be set in the server 104. The content recommendation method provided in the embodiment of the present disclosure can also be executed by a server or server cluster that is different from the server 104 and can communicate with the terminal devices 101, 102, 103 and / or the server 104. Accordingly, the content recommendation device provided in the embodiment of the present disclosure can also be set in a server or server cluster that is different from the server 104 and can communicate with the terminal devices 101, 102, 103 and / or the server 104.

[0028] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to the implementation requirements.

[0029] The present disclosure provides a content recommendation method. Figure 1 The system architecture of Figure 2 to Figure 4 The content recommendation method according to the exemplary embodiment of the present disclosure is described as follows. The content recommendation method of the embodiment of the present disclosure can be, for example, Figure 1 The server 104 is shown to execute.

[0030] Figure 2 The flowchart of the content recommendation method according to an embodiment of the present disclosure is schematically shown.

[0031] like Figure 2 As shown, the content recommendation method 200 of the embodiment of the present disclosure may include, for example, operations S210 to S230.

[0032] In operation S210, in-vehicle scene data is identified to obtain status characteristic information of in-vehicle occupants, the in-vehicle scene data including in-vehicle scene images and / or in-vehicle scene audio.

[0033] In operation S220 , a target content type to be recommended is determined based on the status characteristic information of the vehicle occupant.

[0034] In operation S230, content associated with the target content type is recommended to the in-vehicle terminal.

[0035] The following is an example flow of each operation of the content recommendation method of this embodiment.

[0036] For example, the in-vehicle scene data can be obtained through various public, legal and compliant methods, such as from public data sets, or obtained by a data acquisition terminal after obtaining authorization from a user associated with the in-vehicle scene data. The in-vehicle scene data is not scene data for a specific user and does not reflect the personal information of a specific user. The application scope of the in-vehicle scene data is limited to the scope that the user has the right to know and has authorized to use.

[0037] In response to receiving the in-vehicle scene data, the execution subject of the content recommendation method identifies the in-vehicle scene data and obtains the state characteristic information of the in-vehicle occupants. The in-vehicle scene data can be collected by a data collection terminal, for example, by an in-vehicle camera or an in-vehicle sensor. The in-vehicle scene data includes an in-vehicle scene image and / or an in-vehicle scene audio.

[0038] When identifying the in-car scene data, facial feature recognition can be performed on the in-car scene image, and / or sound feature recognition can be performed on the in-car scene audio to obtain at least one of the following information associated with the in-car occupants: the number of occupants, the gender of the occupants, the estimated age of the occupants, and the emotional characteristics of the occupants. By determining multiple types of state feature information of the in-car occupants, it is helpful to improve the accuracy of state feature recognition, and the diversity of state feature information is helpful to ensure the matching degree between the recommended content and the characteristics of the in-car occupants.

[0039] For example, the symmetric difference method can be used to detect motion information in the in-vehicle scene image, and face detection can be performed based on the clustering characteristics of face skin color in the YCrCb color space. A single face in the in-vehicle scene image can be detected based on a rule-based projection algorithm, and multiple faces in a complex environment in the in-vehicle scene image can also be detected. The number of occupants in the in-vehicle scene image can be determined based on the detected facial information.

[0040] The occupant's emotional characteristics may include an excited emotional state, a normal emotional state, and a tired emotional state. The facial expression characteristics of the characters in the in-vehicle scene image may be extracted, and the occupant's emotional characteristics of the in-vehicle occupant may be determined based on the facial expression characteristics. The facial expression characteristics may include, for example, the distance between the center of the eye and the center and corner of the mouth, and the facial expression characteristics may indicate the emotional state of the in-vehicle occupant.

[0041] The sound characteristics of the in-car scene audio can be recognized, and the number of passengers in the car, the gender of the passengers, the estimated age of the passengers, the emotional state of the passengers, etc. can be determined based on the sound characteristics in the in-car scene audio. The sound characteristics can include, for example, pitch, loudness, timbre, etc.

[0042] According to the state characteristic information of the vehicle occupant, the target content type to be recommended is determined. According to the preset content tag associated with each content type of the at least one content type, a target content tag that satisfies the similarity condition with the state characteristic information of the vehicle occupant is determined, and the content type associated with the target content tag is used as the target content type to be recommended.

[0043] Recommending content associated with a target content type to a vehicle terminal, the vehicle terminal may be, for example, a multimedia player in a vehicle, and the content recommended to the vehicle terminal may include, for example, multimedia data. The vehicle terminal may request a corresponding multimedia data file from a server according to the recommended multimedia data, or obtain the corresponding multimedia data file from a multimedia data list stored in the vehicle terminal.

[0044] Exemplarily, vehicle navigation data may be obtained and identified to obtain the navigation route of the vehicle. The target content type to be recommended may be determined based on the route length of the navigation route and / or the target content type to be recommended may be determined based on the locations along the navigation route.

[0045] When the vehicle is in a navigation state, obtain vehicle navigation data. Identify the vehicle navigation data to obtain the navigation route of the vehicle. In an example manner, determine the route type of the vehicle navigation route according to whether the route length of the navigation route is greater than a preset threshold, and the route type may include short-distance and long-distance. According to the route type of the vehicle navigation route, determine the target content type that matches the route type.

[0046] In another example, the target content type that matches the route location is determined based on the route location in the navigation route. For example, if the navigation route indicates that the destination to be reached by the vehicle is a movie theater, the soundtrack of the recently released movie can be used as the target content type to be recommended. For another example, if the navigation route indicates that the city to be passed by the vehicle includes City A, the introduction to the cultural cuisine associated with City A can be used as the target content type to be recommended.

[0047] By identifying the vehicle navigation data and determining the target content type to be recommended based on the vehicle's navigation route, it is helpful to ensure the matching degree between the content recommendation and the navigation route, and can effectively improve the content recommendation effect.

[0048] The parking state data of the vehicle can be obtained, and when the parking state data indicates that the parking state of the vehicle has changed, the in-vehicle scene data can be obtained again. The parking state includes the parking state and the starting state. When the parking state of the vehicle changes, the situation of the occupants in the vehicle may change. Re-acquiring the in-vehicle scene data can effectively ensure the real-time nature of the in-vehicle scene data. According to the in-vehicle scene data obtained again, the target content type to be recommended is determined, which can effectively ensure the immediacy of the recommended content, and the content recommendation effect is significant.

[0049] When the vehicle is in motion, the in-vehicle scene data can be acquired based on a preset frequency. For example, the in-vehicle scene data is acquired once every 10 minutes, and the target content type to be recommended is determined based on the most recently acquired in-vehicle scene data. The real-time nature of the acquired in-vehicle scene data is conducive to ensuring the immediacy of the recommended content and meeting the diversified content consumption needs generated when the passenger status changes.

[0050] Through the embodiments of the present disclosure, in-vehicle scene data is identified to obtain status characteristic information of the in-vehicle occupants, wherein the in-vehicle scene data includes in-vehicle scene images and / or in-vehicle scene audio. Based on the status characteristic information of the in-vehicle occupants, the target content type to be recommended is determined, and content associated with the target content type is recommended to the in-vehicle terminal.

[0051] Automatically determining the target content type to be recommended based on the status characteristic information of the in-vehicle occupants can effectively improve the efficiency of content acquisition in vehicle scenarios, reduce the search cost and operation difficulty of in-vehicle occupants to obtain content, and help ensure vehicle driving safety. Combining the status characteristic information of in-vehicle occupants for content recommendation is conducive to ensuring the matching degree of content recommendation with the characteristics of in-vehicle occupants, making content recommendation more reasonable and effective.

[0052] Figure 3 The following is a schematic diagram of a content recommendation method according to another embodiment of the present disclosure.

[0053] like Figure 3 As shown, the method 300 may include, for example, operation S210, operation S310, operation S320, and operation S230.

[0054] In operation S210, in-vehicle scene data is identified to obtain status characteristic information of in-vehicle occupants, the in-vehicle scene data including in-vehicle scene images and / or in-vehicle scene audio.

[0055] In operation S310 , a target occupant type with a highest recommendation weight associated with the occupant is determined based on preset recommendation weights associated with the occupant types and status characteristic information of the occupant in the vehicle.

[0056] In operation S320 , a target content type to be recommended is determined based on the state characteristic information of the target occupant type.

[0057] In operation S230, content associated with the target content type is recommended to the in-vehicle terminal.

[0058] The following is an example flow of each operation of the content recommendation method of this embodiment.

[0059] Exemplarily, the state characteristic information of the passengers in the vehicle may include the number of passengers, the gender of the passengers, the estimated age of the passengers, the emotional characteristics of the passengers, the identity of the passengers, etc. According to the state characteristic information, the type of passengers in the vehicle is determined. According to the preset recommendation weight associated with the passenger type and the type of passengers in the vehicle, the target passenger type with the highest recommendation weight is determined. According to the state characteristic information of the target passenger type, the target content type to be recommended is determined.

[0060] For example, the preset recommendation weight associated with young children is the highest, followed by the elderly and young people. When the passengers in the car include young children, the target content type to be recommended is determined based on the number, gender, estimated age, emotional characteristics and other information of the young children. When the passengers in the car do not include young children and the elderly, the target content type to be recommended is determined based on the number, gender, estimated age, emotional characteristics and other information of the young people. For example, when the passengers in the car include multiple young people, the corresponding in-car scene may be a scene of a group outing for young people, and happy and relaxing music can be used as the target content type to be recommended.

[0061] When determining the target content type to be recommended based on the state characteristic information of the target occupant type, the target content label that satisfies the similarity condition with the state characteristic information of the target occupant type can be determined based on the preset content label associated with each content type of at least one content type, and the content type associated with the target content label is used as the target content type to be recommended. By determining the target occupant type with the highest recommendation weight, content recommendation is performed based on the state characteristic information of the target occupant type, which is conducive to effectively improving the content recommendation efficiency and effectively ensuring the content recommendation effect.

[0062] After recommending content to the vehicle terminal, the occupant interaction information for the recommended content can be obtained. Based on the occupant interaction information, the recommendation value evaluation value associated with the recommended content is determined, and the recommendation value evaluation value indicates the degree of interest of the occupants in the vehicle in the recommended content. When the recommendation value evaluation value is lower than the preset threshold, the content label classification for the content type and / or the recommendation weight associated with the occupant type are adjusted. By optimizing the content recommendation process, the efficiency of content recommendation can be effectively improved, and the reliability of content recommendation can be improved.

[0063] After recommending content to the vehicle terminal, at least one of the following interactive information for the recommended content can be obtained: playback completeness, playback switching record, number of repeated playbacks, and number of shares and favorites. The playback switching methods include voice switching, screen click switching, and square control switching. Square control switching includes switching content through multimedia control buttons on the vehicle steering wheel.

[0064] For example, the number of times content i is recommended is N. i , the recommendation value evaluation value E of content i i It can be expressed as E i =(m*C i +n*R i -X i ), m, n are preset coefficients, C i represents the number of times content i is shared and collected, R i represents the number of repeated playbacks of content i, X i Indicates the number of times the playback completeness is less than the preset completeness threshold. Recommended value evaluation value E i The degree of interest of the vehicle occupants in the content i may be indicated.

[0065] After recommending content to the vehicle terminal, the in-vehicle scene image and / or in-vehicle scene audio may be acquired again. The in-vehicle scene image acquired again may be subjected to facial feature recognition to obtain the emotional features of the in-vehicle occupants. The in-vehicle scene audio acquired again may be subjected to voice content recognition to obtain the content evaluation information of the in-vehicle occupants, or the in-vehicle scene audio acquired again may be subjected to sound feature recognition to obtain the emotional features of the in-vehicle occupants. The emotional features of the occupants and / or the content evaluation information constitute the occupant interaction information for the recommended content.

[0066] After recommending content to the vehicle terminal, the in-vehicle scene image is obtained again. The in-vehicle scene image is recognized to obtain the occupant's emotional characteristics and / or content evaluation information after the content recommendation. According to the occupant's emotional characteristics and / or content evaluation information, it is determined whether the occupant's feedback on the recommended content is positive feedback or negative feedback. Optimizing content recommendation based on occupant interaction information is conducive to effectively improving content recommendation efficiency and improving content recommendation effects.

[0067] When the recommendation value evaluation value of the recommended content is lower than the preset threshold, the content recommendation process is optimized. For example, the content tag classification for the content type can be adjusted, and / or the recommendation weight associated with the occupant type can be adjusted. By optimizing the content tag classification for the content type, the matching accuracy of the content to be recommended can be effectively improved. By optimizing the recommendation weight for the occupant type, it is conducive to dynamically optimizing the content recommendation method according to the preferences and content consumption habits of the occupants in the car, which is conducive to improving the content recommendation effect and improving the content recommendation efficiency.

[0068] The recommendation pool may be a collection of content including at least one content type. Content associated with the target content type may include content in a first recommendation pool, and the content in the first recommendation pool corresponds to a first recommendation number threshold. When the recommended content is content in the first recommendation pool and the corresponding recommendation value evaluation value is lower than a preset threshold, the recommended content may be transferred from the first recommendation pool to a second recommendation pool. The content in the second recommendation pool corresponds to a second recommendation number threshold, and the second recommendation number threshold is less than the first recommendation number threshold.

[0069] The content associated with the target content type may include content in the second recommendation pool. When the recommended content is content in the second recommendation pool and the corresponding recommendation value evaluation value is lower than a preset threshold, the recommended content is transferred from the second recommendation pool to the third recommendation pool. The content in the third recommendation pool corresponds to a third recommendation number threshold, and the third recommendation number threshold is lower than the second recommendation number threshold. When the storage time of any content in the third recommendation pool exceeds a preset time threshold, the content is treated as invalid content.

[0070] According to the recommendation value evaluation value of the recommended content, the threshold of the number of recommendations for the content is dynamically adjusted. According to the status characteristic information of the passengers in the car and the feedback information of the passengers in the car on the recommended content, a list of content to be recommended is constructed. The diversified content consumption needs of different passenger status characteristics are met in an automated manner, which can effectively reduce the content search and screening operations of the passengers on the vehicle terminal, and can effectively ensure the content recommendation effect in the vehicle scene, which is conducive to improving the satisfaction of the passengers in the car and ensuring the safety of vehicle driving.

[0071] Figure 4 The following is a schematic diagram schematically showing a content recommendation process according to an embodiment of the present disclosure.

[0072] like Figure 4As shown, in the content recommendation process 400, the data acquisition terminal in the vehicle 401 sends the in-vehicle scene data to the server 402. The server 402 identifies the received in-vehicle scene data and obtains the state characteristic information of the in-vehicle occupants in the vehicle 401. The server 402 determines the target content type to be recommended based on the state characteristic information of the in-vehicle occupants, and recommends the content associated with the target content type to the in-vehicle terminal in the vehicle 401. The in-vehicle terminal can be, for example, a multimedia data file playback device in the vehicle 401.

[0073] When determining the target content type to be recommended, the server 402 may determine the target content tag that satisfies the similarity condition with the state characteristic information of the vehicle occupant according to the preset content tag associated with each content type of the at least one content type, and use the content type associated with the target content tag as the target content type to be recommended. The preset content tag associated with the content type may be marked by the content processing terminal 403.

[0074] Figure 5 The block diagram schematically shows a content recommendation device according to an embodiment of the present disclosure.

[0075] like Figure 5 As shown, the content recommendation device 500 according to the embodiment of the present disclosure includes, for example, a first processing module 510 , a second processing module 520 and a third processing module 530 .

[0076] The first processing module 510 is used to identify the in-vehicle scene data to obtain the status characteristic information of the in-vehicle occupants, and the in-vehicle scene data includes the in-vehicle scene image and / or the in-vehicle scene audio; the second processing module 520 is used to determine the target content type to be recommended based on the status characteristic information of the in-vehicle occupants; and the third processing module 530 is used to recommend content associated with the target content type to the in-vehicle terminal.

[0077] Through the embodiments of the present disclosure, in-vehicle scene data is identified to obtain status characteristic information of the in-vehicle occupants, wherein the in-vehicle scene data includes in-vehicle scene images and / or in-vehicle scene audio. Based on the status characteristic information of the in-vehicle occupants, the target content type to be recommended is determined, and content associated with the target content type is recommended to the in-vehicle terminal.

[0078] Automatically determining the target content type to be recommended based on the status characteristic information of the in-vehicle occupants can effectively improve the efficiency of content acquisition in vehicle scenarios, reduce the search cost and operation difficulty of in-vehicle occupants to obtain content, and help ensure vehicle driving safety. Combining the status characteristic information of in-vehicle occupants for content recommendation is conducive to ensuring the matching degree of content recommendation with the characteristics of in-vehicle occupants, making content recommendation more reasonable and effective.

[0079] According to an embodiment of the present disclosure, the first processing module includes: a first processing sub-module, which is used to perform facial feature recognition on the in-vehicle scene image, and / or perform sound feature recognition on the in-vehicle scene audio, to obtain at least one of the following information associated with the occupants in the vehicle: the number of occupants, the gender of the occupants, the estimated age of the occupants, and the emotional characteristics of the occupants.

[0080] According to an embodiment of the present disclosure, the second processing module includes: a second processing sub-module, used to determine the target occupant type with the highest recommendation weight associated with the occupant type and the status characteristic information of the occupant in the vehicle; and a third processing sub-module, used to determine the target content type to be recommended based on the status characteristic information of the target occupant type.

[0081] According to an embodiment of the present disclosure, the third processing submodule includes: a first processing unit, used to determine, based on a preset content tag associated with each content type of at least one content type, a target content tag that satisfies a similarity condition with the state characteristic information of the target occupant type; and a second processing unit, used to use the content type associated with the target content tag as the target content type to be recommended.

[0082] According to an embodiment of the present disclosure, the device also includes: a fourth processing module, used to obtain occupant interaction information for the recommended content after recommending the content to the vehicle-mounted terminal; a fifth processing module, used to determine a recommendation value evaluation value associated with the recommended content based on the occupant interaction information, wherein the recommendation value evaluation value indicates the degree of interest of the occupants in the vehicle in the recommended content; and a sixth processing module, used to adjust the content tag classification for the content type and / or adjust the recommendation weight associated with the occupant type when the recommendation value evaluation value is lower than a preset threshold.

[0083] According to an embodiment of the present disclosure, the fourth processing module includes: a fourth processing sub-module, which is used to obtain at least one of the following interactive information for the recommended content after recommending content to the vehicle-mounted terminal: playback completeness, playback switching record, number of repeated playbacks, and number of shares and collections, wherein the playback switching methods include voice switching, screen click switching, and square control switching, and the square control switching includes a method of switching content through the multimedia control buttons on the vehicle steering wheel.

[0084] According to an embodiment of the present disclosure, the fourth processing module includes: a fifth processing sub-module, which is used to re-acquire in-vehicle scene images and / or in-vehicle scene audio after recommending content to the vehicle-mounted terminal; a sixth processing sub-module, which is used to perform facial feature recognition on the re-acquired in-vehicle scene images to obtain occupant emotional characteristics of the in-vehicle occupants, and / or perform voice content recognition on the re-acquired in-vehicle scene audio to obtain content evaluation information of the in-vehicle occupants; and a seventh processing sub-module, which is used for the occupant emotional characteristics and / or content evaluation information to constitute occupant interaction information for the recommended content.

[0085] According to an embodiment of the present disclosure, the content associated with the target content type includes content located in a first recommendation pool, and the content in the first recommendation pool corresponds to a first recommendation number threshold; the device also includes: a seventh processing module, used to transfer the recommended content from the first recommendation pool to the second recommendation pool when the recommendation value evaluation value of the recommended content is lower than a preset threshold; the content in the second recommendation pool corresponds to a second recommendation number threshold, and the second recommendation number threshold is less than the first recommendation number threshold.

[0086] According to an embodiment of the present disclosure, the device also includes an eighth processing module, which is used to: identify vehicle navigation data to obtain the vehicle's navigation route; and determine the target content type to be recommended based on the route length of the navigation route; and / or determine the target content type to be recommended based on the passing locations in the navigation route.

[0087] According to an embodiment of the present disclosure, the device also includes a ninth processing module, which is used to: obtain parking status data of the vehicle; when the parking status data indicates that the parking status of the vehicle has changed, obtain in-vehicle scene data again, and the parking status includes a parking state and a starting state; and determine the target content type to be recommended based on the in-vehicle scene data obtained again.

[0088] It should be noted that the information collection, storage, use, processing, transmission, provision and disclosure involved in the technical solution of the present disclosure are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0089] 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.

[0090] Figure 6 A block diagram of an electronic device for performing content recommendation according to an embodiment of the present disclosure is schematically shown.

[0091] Figure 6A schematic block diagram of an example electronic device 600 that can be used to implement an embodiment of the present disclosure is shown. The electronic device 600 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.

[0092] like Figure 6 As shown, the device 600 includes a computing unit 601, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 602 or a computer program loaded from a storage unit 608 into a random access memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the device 600 can also be stored. The computing unit 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0093] A number of components in the device 600 are connected to the I / O interface 605, including: an input unit 606, such as a keyboard, a mouse, etc.; an output unit 607, such as various types of displays, speakers, etc.; a storage unit 608, such as a disk, an optical disk, etc.; and a communication unit 609, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 609 allows the device 600 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0094] The computing unit 601 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 601 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 601 performs the various methods and processes described above, such as the content recommendation method. For example, in some embodiments, the content recommendation method may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 608. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 600 via the ROM 602 and / or the communication unit 609. When the computer program is loaded into the RAM 603 and executed by the computing unit 601, one or more steps of the content recommendation method described above may be performed. Alternatively, in other embodiments, the computing unit 601 may be configured to perform the content recommendation method in any other appropriate manner (e.g., by means of firmware).

[0095] 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.

[0096] 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 data processing 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 and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0097] 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.

[0098] To provide interaction with an object, 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 object; and a keyboard and pointing device (e.g., a mouse or trackball) through which the object can provide input to the computer. Other types of devices can also be used to provide interaction with an object; for example, the feedback provided to the object can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the object can be received in any form (including acoustic input, voice input, or tactile input).

[0099] The systems and techniques described herein may be implemented in a computing system that includes back-end 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 front-end components (e.g., an object computer having a graphical object interface or a web browser through which the object can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communications network). Examples of communications networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0100] 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 of client and server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0101] 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.

[0102] 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. A content recommendation method, comprising: Identify the in-vehicle scene data to obtain the status characteristic information of the in-vehicle occupants, wherein the in-vehicle scene data includes in-vehicle scene images and / or in-vehicle scene audio; Determining the target content type to be recommended according to the status characteristic information of the vehicle occupant; and recommending content associated with the target content type to the vehicle-mounted terminal; Wherein, determining the target content type to be recommended according to the state characteristic information of the vehicle occupant includes: Determining a target occupant type from the occupants in the vehicle according to the state characteristic information of the occupants in the vehicle; Determining, based on a preset content tag associated with each of the at least one content type, a target content tag that satisfies a similarity condition with the state characteristic information of the target occupant type; and Using the content type associated with the target content tag as the target content type to be recommended; The method further comprises: Acquire a recommendation value evaluation value associated with the recommended content, wherein the recommendation value evaluation value indicates the interest level of the vehicle occupant in the recommended content; and When the recommendation value evaluation value is lower than a preset threshold, the content tag classification for the content type and / or the recommendation weight associated with the occupant type is adjusted.

2. The method according to claim 1, wherein: The identifying of the in-vehicle scene data to obtain the status characteristic information of the in-vehicle occupants includes: Perform facial feature recognition on the in-vehicle scene image, and / or perform sound feature recognition on the in-vehicle scene audio to obtain at least one of the following information associated with the in-vehicle occupant: The number of occupants, occupant gender, occupant estimated age, and occupant emotional characteristics.

3. The method according to claim 1, wherein: Determining the target occupant type from the occupants in the vehicle according to the state characteristic information comprises: Determining a target occupant type with a highest recommendation weight associated with the occupant type according to preset recommendation weights associated with the occupant types and the state characteristic information of the occupant in the vehicle; The determining of the target content type to be recommended according to the state characteristic information of the vehicle occupant comprises: The target content type to be recommended is determined according to the state characteristic information of the target occupant type.

4. According to the method of claim 1, the recommendation value evaluation value is determined by: After recommending content to the vehicle-mounted terminal, obtaining passenger interaction information for the recommended content; A recommendation value evaluation value associated with the recommended content is determined according to the occupant interaction information.

5. The method according to claim 4, wherein: After recommending content to the vehicle-mounted terminal, obtaining passenger interaction information for the recommended content includes: After recommending content to the vehicle-mounted terminal, obtaining at least one of the following interactive information for the recommended content: Playback completeness, playback switching records, number of repeated playbacks, sharing and collection times, Among them, the playback switching methods include voice switching, screen click switching and square control switching, and the square control switching includes switching content through the multimedia control buttons on the vehicle steering wheel.

6. The method according to claim 4, wherein: After recommending content to the vehicle-mounted terminal, obtaining passenger interaction information for the recommended content includes: After recommending the content to the vehicle-mounted terminal, acquiring the in-vehicle scene image and / or in-vehicle scene audio again; Performing facial feature recognition on the reacquired in-vehicle scene image to obtain the occupant's emotional features, and / or performing voice content recognition on the reacquired in-vehicle scene audio to obtain content evaluation information of the occupant; and The occupant emotional characteristics and / or the content evaluation information constitute occupant interaction information for the recommended content.

7. The method according to claim 4, wherein: The content associated with the target content type includes content in a first recommendation pool, and the content in the first recommendation pool corresponds to a first recommendation number threshold; The method further comprises: When the recommendation value evaluation value of the recommended content is lower than a preset threshold, transferring the recommended content from the first recommendation pool to the second recommendation pool; Among them, the content in the second recommendation pool corresponds to a second recommendation number threshold, and the second recommendation number threshold is smaller than the first recommendation number threshold.

8. The method according to any one of claims 1 to 7, further comprising: Identify vehicle navigation data to obtain the vehicle's navigation route; as well as Determining the target content type to be recommended according to the route length of the navigation route; And / or determining the target content type to be recommended according to the places along the navigation route.

9. The method according to any one of claims 1 to 7, further comprising: Obtaining the parking status data of the vehicle; When the parking state data indicates that the parking state of the vehicle has changed, acquiring the in-vehicle scene data again, wherein the parking state includes a parking state and a starting state; as well as The target content type to be recommended is determined according to the in-vehicle scene data acquired again.

10. A content recommendation device, comprising: A first processing module is used to identify the in-vehicle scene data to obtain the status characteristic information of the in-vehicle occupants, wherein the in-vehicle scene data includes an in-vehicle scene image and / or an in-vehicle scene audio; A second processing module is used to determine the target content type to be recommended according to the state characteristic information of the vehicle occupant; and A third processing module, configured to recommend content associated with the target content type to the vehicle-mounted terminal; Wherein, the second processing module includes: a determination submodule, configured to determine a target occupant type from the occupants in the vehicle according to the state characteristic information of the occupants in the vehicle; a first processing unit, configured to determine, based on a preset content tag associated with each of the at least one content type, a target content tag that satisfies a similarity condition with the state feature information of the target occupant type; and A second processing unit, configured to use the content type associated with the target content tag as the target content type to be recommended; The device also includes: an acquisition module, configured to acquire a recommendation value evaluation value associated with the recommended content, wherein the recommendation value evaluation value indicates the interest level of the vehicle occupant in the recommended content; and The sixth processing module is used to adjust the content tag classification for the content type and / or adjust the recommendation weight associated with the occupant type when the recommendation value evaluation value is lower than a preset threshold.

11. The device according to claim 10, wherein: The first processing module comprises: The first processing submodule is configured to perform facial feature recognition on the in-vehicle scene image and / or sound feature recognition on the in-vehicle scene audio to obtain at least one of the following information associated with the in-vehicle occupant: The number of occupants, occupant gender, occupant estimated age, and occupant emotional characteristics.

12. The device according to claim 10, wherein: The determination submodule comprises: A second processing submodule, configured to determine a target occupant type with the highest recommendation weight associated with the occupant type and the state characteristic information of the occupant in the vehicle according to the preset recommendation weight associated with the occupant type; The second processing module comprises: The third processing submodule is used to determine the target content type to be recommended according to the state characteristic information of the target occupant type.

13. The device according to claim 10, wherein the recommendation value evaluation value is determined by the following modules: A fourth processing module, configured to obtain passenger interaction information for the recommended content after recommending the content to the vehicle-mounted terminal; The fifth processing module is used to determine a recommendation value evaluation value associated with the recommended content according to the passenger interaction information.

14. The device according to claim 13, wherein: The fourth processing module comprises: The fourth processing submodule is configured to obtain at least one of the following interactive information for the recommended content after recommending the content to the vehicle-mounted terminal: Playback completeness, playback switching records, number of repeated playbacks, sharing and collection times, Among them, the playback switching methods include voice switching, screen click switching and square control switching, and the square control switching includes switching content through the multimedia control buttons on the vehicle steering wheel.

15. The device according to claim 13, wherein: The fourth processing module comprises: A fifth processing submodule, configured to obtain again the in-vehicle scene image and / or in-vehicle scene audio after recommending the content to the in-vehicle terminal; a sixth processing submodule, configured to perform facial feature recognition on the reacquired in-vehicle scene image to obtain the occupant's emotional features, and / or perform voice content recognition on the reacquired in-vehicle scene audio to obtain content evaluation information of the occupant; and The seventh processing submodule is used for forming the passenger interaction information for the recommended content based on the passenger emotion characteristics and / or the content evaluation information.

16. The device according to claim 13, wherein: The content associated with the target content type includes content in a first recommendation pool, and the content in the first recommendation pool corresponds to a first recommendation number threshold; The device also includes: A seventh processing module, configured to transfer the recommended content from the first recommendation pool to a second recommendation pool when the recommendation value evaluation value of the recommended content is lower than a preset threshold; Among them, the content in the second recommendation pool corresponds to a second recommendation number threshold, and the second recommendation number threshold is smaller than the first recommendation number threshold.

17. The apparatus according to any one of claims 10 to 16, further comprising an eighth processing module, configured to: Identify the vehicle navigation data to obtain the vehicle's navigation route; and The target content type to be recommended is determined according to the route length of the navigation route; and / or the target content type to be recommended is determined according to the passing places in the navigation route.

18. The apparatus according to any one of claims 10 to 16, further comprising a ninth processing module, configured to: Obtaining the parking status data of the vehicle; When the parking state data indicates that the parking state of the vehicle has changed, the in-vehicle scene data is acquired again, wherein: The parking state includes a parking state and a starting state; as well as The target content type to be recommended is determined according to the in-vehicle scene data acquired again.

19. An electronic device comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can 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 any one of claims 1 to 9.

20. 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 to 9.

21. A computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the computer program implements the method according to any one of claims 1 to 9.

Images