Service content active recommendation method and device based on user character, equipment and vehicle

Abstract

The invention provides a service content active recommendation method and device based on user characters, equipment and a vehicle. The service content active recommendation method based on the user characters comprises the steps of obtaining user comprehensive data of a user; determining a character type of the user according to the user comprehensive data; determining service content to be recommended from a preset service content database based on the character type; and recommending the service content to be recommended to the user in a voice form and / or a visual form. The service content is actively recommended for the user through character classification of the user, and personalized requirements of different users can be more accurately met.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and specifically to a method, device, equipment and vehicle for actively recommending service content based on user personality. Background Art

[0002] With the rapid advancement of artificial intelligence technology, the service functions of smart cockpits are gradually enriched. Smart cockpits can assist drivers in completing various commands, such as playing music, navigating, making calls, etc., which greatly enriches people's driving life.

[0003] However, existing smart cockpits have significant limitations in providing services. Most existing smart cockpits adopt a passive service mode, that is, they can only perform corresponding operations after the user explicitly issues an instruction. This mode requires the user to actively trigger the interaction, while the smart cockpit is in a waiting state and passively responds to the user's instructions. As a result, the existing smart cockpit lacks personalized services for users when providing services, cannot meet the personalized needs of users, increases the user's operating burden, and reduces the smoothness and convenience of the user experience. Summary of the invention

[0004] In view of the above content, it is necessary to propose a method, device, equipment and vehicle for actively recommending service content based on user personality, so as to solve the technical problems that the existing smart cockpit lacks personalized services for users when providing services, cannot meet the personalized needs of users, increases the user's operating burden, and reduces the smoothness and convenience of user experience.

[0005] In a first aspect, the present application provides a method for actively recommending service content based on user personality, the method comprising: obtaining comprehensive user data of the user; determining the personality type of the user based on the comprehensive user data; based on the personality type, determining the service content to be recommended from a preset service content database; and recommending the service content to be recommended to the user in voice form and / or visual form.

[0006] In the method for actively recommending service content based on user personality in the above-mentioned embodiment, personality analysis is performed using comprehensive user data, and different service content is recommended to users of different personality types, which provides deeper user insights, improves the accuracy of recommended content, and can more accurately meet the personalized needs of different users, improves the accuracy of service recommendations, and realizes active recommendation of services without disturbing users too much, thereby improving user experience. Actively recommending services to users based on their personality types improves service efficiency, and users can obtain the required information more quickly without waiting or performing additional operations, making it smoother and more convenient for users to use the service functions of the smart cockpit. Recommending recommended content to the user in voice and / or visual form makes the interaction more natural and intuitive. The voice form is particularly suitable for use in driving scenarios and can ensure driving safety.

[0007] In some embodiments of the present application, the comprehensive user data includes portrait data of the user and / or historical behavior data of the user; wherein, the portrait data includes basic information of the user, the frequency of use of each function of the voice assistant by the user, and the model and price of the vehicle purchased by the user; the historical behavior data includes the historical interaction behavior of the user with the voice assistant, and the historical control behavior of the user using the vehicle.

[0008] In some embodiments of the present application, the method further includes: obtaining a representation vector of the personality type based on the portrait data and / or the historical behavior data.

[0009] In some embodiments of the present application, the method further includes: obtaining a representation vector of the portrait data and a representation vector of the historical behavior data; and obtaining a representation vector of the personality type based on the representation vector of the portrait data and / or the representation vector of the historical behavior data.

[0010] In some embodiments of the present application, the method further includes: obtaining a representation vector of each service content in the service content database.

[0011] In some embodiments of the present application, determining the service content to be recommended from a preset service content database based on the personality type includes: determining the service content corresponding to the personality type from the service content database; determining, based on a trained matching model, a matching value between a representation vector of the personality type and a representation vector of each service content corresponding to the personality type; and using the service content whose matching value is a preset value as the service content to be recommended.

[0012] In some embodiments of the present application, the training method of the matching model includes: obtaining sample portrait data and / or sample behavior data of multiple users associated with each sample service content in the service content database and obtaining a representation vector of each sample service content; obtaining a representation vector of the sample personality type of each user based on the sample portrait data and / or the sample behavior data of each user; obtaining a matching value label between the representation vector of the sample personality type of each user and the representation vector of each sample service content; establishing a training data set, the training data set including multiple training samples, each training sample including a representation vector of the sample personality type, a representation vector of the sample service content, and a matching value label between the representation vector of the sample personality type and the representation vector of the sample service content; using the training data set to train a preset model to obtain the trained matching model. In some embodiments of the present application, determining the personality type of the user based on the user's comprehensive data includes: performing a multi-dimensional personality analysis on the user based on the user's comprehensive data to obtain a multi-dimensional personality analysis result of the user; based on the multi-dimensional personality analysis result, performing personality classification matching on the user through a preset machine learning algorithm to determine the user's personality type.

[0013] In a second aspect, the present application also provides a device for actively recommending service content based on user personality, the device comprising: an acquisition module for acquiring comprehensive user data of the user; a first determination module for determining the personality type of the user based on the comprehensive user data; a second determination module for determining the service content to be recommended from a preset service content database based on the personality type; and a recommendation module for recommending the service content to be recommended to the user in voice and / or visual form.

[0014] In a third aspect, the present application also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program, when executed by the processor, implements the steps of the method for actively recommending service content based on user personality as described in the above embodiment.

[0015] In a fourth aspect, the present application also provides a vehicle, which includes the electronic device described in the above embodiment.

[0016] It can be understood that the second aspect of the active service content recommendation device based on user personality, the third aspect of the electronic device and the fourth aspect of the vehicle provided above all correspond to the first aspect of the active service content recommendation method based on user personality. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects of the corresponding active service content recommendation method based on user personality provided above, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 This is a schematic diagram of an application scenario of a method for actively recommending service content based on user personality provided in an embodiment of the present application.

[0018] Figure 2 It is a flowchart of a method for actively recommending service content based on user personality provided by an embodiment of the present application.

[0019] Figure 3 It is a flowchart of a method for actively recommending service content based on user personality provided by another embodiment of the present application.

[0020] Figure 4 It is a detailed flow chart of step S22 in the method for actively recommending service content based on user personality provided in one embodiment of the present application.

[0021] Figure 5 It is a flowchart of a training method for a matching model provided in one embodiment of the present application.

[0022] Figure 6 It is a schematic diagram of functional modules of a device for actively recommending service content based on user personality provided in one embodiment of the present application.

[0023] Component Symbols Vehicle 1 Electronic devices 10 Memory 11 Processor 12 Speaker 20 Speaker 30 Service content active recommendation device 100 Acquisition module 110 The first determination module 120 Second determination module 130 Recommended Module 140 The following specific implementation methods will further illustrate the present application in conjunction with the above-mentioned drawings. DETAILED DESCRIPTION

[0024] The embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present application, and cannot be understood as limiting the present application.

[0025] In the embodiments of the present application, it should be noted that, unless otherwise clearly specified and limited, words such as "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "for example" is intended to present related concepts in a specific way.

[0026] In the description of this application, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection, an electrical connection, or mutual communication; it can be a direct connection, or an indirect connection through an intermediate medium, it can be the internal connection of two elements or the interaction relationship between two elements. For ordinary technicians in this field, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0027] In the description of the present application, it should be noted that, unless otherwise expressly specified and limited, the terms "first" and "second" are used for descriptive purposes only and cannot be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In addition, in the description of the present application, the meaning of "plurality" is two or more, unless otherwise clearly and specifically limited.

[0028] In order to more clearly understand the above-mentioned purpose, features and advantages of the present invention, the present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.

[0029] See also Figure 1 , which is a schematic diagram of an application scenario of a method for actively recommending service content based on user personality provided in an embodiment of the present application.

[0030] The embodiment of the present application provides a method for actively recommending service content based on user personality, which can be applied to one or more electronic devices 10. The electronic device 10 is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to a microprocessor, an application specific integrated circuit (Application Specific Integrated Circuit, ASIC), a programmable gate array (Field-Programmable Gate Array, FPGA), a digital processor (Digital Signal Processor, DSP), an embedded device, etc.

[0031] Specifically, the electronic device 10 is used to determine the personality type of the user according to the comprehensive data of the user; based on the personality type, determine the service content to be recommended from a preset service content database; and recommend the service content to be recommended to the user in voice form and / or visual form.

[0032] In some embodiments of the present application, the electronic device 10 can be communicatively connected to a desktop computer, a notebook, a PDA, a cloud server, or other devices.

[0033] In some embodiments of the present application, the electronic device 10 can perform human-computer interaction with the user through a keyboard, a mouse, a remote control, a touch pad, or a voice control device.

[0034] In some embodiments of the present application, the electronic device 10 may also include a network device and / or a client device. The network device includes but is not limited to a single network server, a server group consisting of multiple network servers, and a cloud server consisting of a large number of hosts or network servers based on cloud computing.

[0035] In some embodiments of the present application, the network where the electronic device 10 is located includes but is not limited to the Internet, a wide area network, a metropolitan area network, a local area network, a virtual private network (VPN), etc.

[0036] In some embodiments of the present application, the present application further provides a vehicle 1, which includes an electronic device 10. The electronic device 10 may be an onboard device of the vehicle 1, such as a body control module (BCM), a vehicle control unit (VCU), etc.

[0037] In some embodiments of the present application, the vehicle 1 may further include a speaker 20 and a display 30. The electronic device 10 is in communication with the speaker 20 and the display 30. The speaker 20 is used to output the service content to be recommended in the form of voice. The display 30 is used to output the service content to be recommended in the form of visual.

[0038] See also Figure 2 , is a schematic diagram of the steps of a method for actively recommending service content based on user personality provided in one embodiment of the present application.

[0039] Specifically, the method for actively recommending service content based on user personality includes the following steps. According to different requirements, the order of some steps in the flowchart can be changed, and some steps can be omitted.

[0040] Step S10, obtaining comprehensive user data of the user.

[0041] In some embodiments of the present application, the user comprehensive data includes but is not limited to the user's portrait data and the user's historical behavior data. The portrait data includes but is not limited to the user's basic information (such as age, gender, occupation, etc.), the frequency of use of each function of the voice assistant (such as navigation function, entertainment function, calling function, etc.) by the user, and the model and price of the vehicle 1 purchased by the user.

[0042] The electronic device 10 may obtain the user's portrait data through user registration information, questionnaires, or third-party data providers.

[0043] In some embodiments of the present application, historical behavior data includes but is not limited to the historical interaction behavior between the user and the voice assistant (such as the conversation records between the user and the voice assistant, the user's specific commands to the voice assistant, etc.), the user's historical control behavior of using vehicle 1 (such as the user's control of service functions through the physical switches or virtual switches of vehicle 1, the time and frequency of the user's use of vehicle 1, etc.).

[0044] Among them, the physical switch of the vehicle 1 refers to a physical button, knob, switch, etc., and the virtual switch refers to a virtual button displayed on the touch screen.

[0045] The user's service function control behaviors through the physical switches or virtual switches of the vehicle 1 may include but are not limited to opening / closing windows, adjusting seats, etc.

[0046] The electronic device 10 may collect the user's historical behavior data from the historical service log of the vehicle 1 .

[0047] In some embodiments of the present application, the user comprehensive data may also include the user's historical voice data and the user's historical text data. Among them, the user's historical voice data includes but is not limited to the voice content and voice features (such as speech speed, pitch, volume, rhythm, emotion, etc.) of the user's interaction with the voice assistant. The user's historical text data includes but is not limited to query records, interactive texts, user feedback, etc. for the service content of vehicle 1. After the electronic device 10 obtains the voice content of the user's interaction with the voice assistant, it needs to convert the user's voice content into text data for subsequent analysis and processing.

[0048] It should be noted that the electronic device 10 strictly abides by the privacy protection policy to ensure that all data acquisition and processing are carried out within the scope of user consent and permitted by laws and regulations.

[0049] In some embodiments of the present application, after obtaining the user's comprehensive data, the electronic device 10 may also preprocess the user's comprehensive data. For example, the preprocessing may include but is not limited to cleaning and formatting operations, such as removing invalid or erroneous data entries, filling missing values, converting data formats, etc., to ensure the quality and consistency of the user's comprehensive data.

[0050] Step S11, determining the user's personality type based on the user's comprehensive data.

[0051] Specifically, step S11, the step of determining the user's personality type based on the user's comprehensive data specifically includes: performing a multi-dimensional personality analysis on the user based on the user's comprehensive data to obtain the user's multi-dimensional personality analysis results; based on the multi-dimensional personality analysis results, performing personality classification and matching on the user through a preset machine learning algorithm to determine the user's personality type.

[0052] Among them, based on psychological theories, such as the five personality trait models (such as openness, responsibility, extroversion, agreeableness, and neuroticism), the user's comprehensive data is analyzed to extract personality-related features. For example, the user's usage habits can be determined based on the frequency of use of each function of the voice assistant by the user; the user's interaction habits can be determined based on the user's interaction behavior with the voice assistant; the user's entertainment and life behaviors using the voice assistant can determine the user's behavioral habits. The extracted features are input into the machine learning algorithm (such as decision tree, support vector machine, neural network, etc.) to obtain the user's personality type, such as extroversion, introversion, rationality, emotionality, etc., and a personality profile containing a detailed description of the personality type is generated for each personality type.

[0053] Step S12: determining the service content to be recommended from a preset service content database based on the personality type.

[0054] Specifically, the preset service content database stores multiple service contents, including but not limited to voice services of a voice assistant (such as reminders, suggestions, greetings, etc.), entertainment services of vehicle 1 (such as playing music, playing news, etc.), control services of vehicle 1 (such as opening and closing windows, adjusting seats, etc.), etc.

[0055] Associate each service content with a personality type. For example, an "extrovert" user may prefer vibrant entertainment information. Based on the personality type, determine the service content corresponding to the personality type from the service content database as the service content to be recommended using a preset recommendation algorithm (such as collaborative filtering, content recommendation, hybrid recommendation, etc.).

[0056] Step S13: recommend the service content to be recommended to the user in voice form and / or visual form.

[0057] In some embodiments of the present application, the service content to be recommended is converted into voice data based on a preset deep learning algorithm, the voice data is output through the speaker 20, and the service content to be recommended is provided to the user in voice form, thereby realizing active recommendation of service content to the user, which is particularly suitable for use in driving scenarios and can ensure driving safety.

[0058] In some embodiments of the present application, the electronic device 10 sends the content to be recommended to the display 30, displays the service content to be recommended through the display 30, and provides the service content to be recommended to the user in a visual form, thereby actively recommending service content to the user, making the interaction more natural and intuitive.

[0059] In the method for actively recommending service content based on user personality in the above-mentioned embodiment, personality analysis is performed using comprehensive user data, and different service content is recommended for users with different personality types, which provides deeper user insights, improves the accuracy of recommended content, and can more accurately meet the personalized needs of different users, improves the accuracy of service recommendations, and realizes active service recommendations without disturbing users too much, thereby improving user experience. Actively recommending services to users based on their personality types improves service efficiency, and users can obtain the required information faster without waiting or performing additional operations, making it smoother and more convenient for users to use the service functions of the smart cockpit. Recommending recommended content to users in voice and / or visual form makes the interaction more natural and intuitive.

[0060] See also Figure 3 , which is a schematic diagram of the steps of a method for actively recommending service content based on user personality provided in another embodiment of the present application.

[0061] Step S20, obtaining comprehensive user data of the user.

[0062] It should be noted that how to obtain the comprehensive data of the user is described in detail in step S10 of the above embodiment, and will not be repeated here to avoid repetition.

[0063] Step S21, determining the user's personality type based on the user's comprehensive data.

[0064] It should be noted that how to determine the personality type of the user based on the user's comprehensive data is described in detail in step S11 of the above embodiment, and will not be repeated here to avoid repetition.

[0065] Step S22, obtaining a representation vector of the personality type based on the portrait data and / or the historical behavior data.

[0066] In some embodiments of the present application, the specific steps of obtaining the representation vector of the personality type based on the portrait data include: obtaining the representation vector of the portrait data; and using the representation vector of the portrait data as the representation vector of the personality type.

[0067] In some embodiments of the present application, the specific steps of obtaining the representation vector of the personality type according to the historical behavior data include: obtaining the representation vector of the historical behavior data; and using the representation vector of the historical behavior data as the representation vector of the personality type.

[0068] In some embodiments of the present application, the specific steps of obtaining the representation vector of the personality type based on the portrait data and the historical behavior data include: obtaining the representation vector of the portrait data and the representation vector of the historical behavior data; and obtaining the representation vector of the personality type based on the representation vector of the portrait data and / or the representation vector of the historical behavior data.

[0069] It should be noted that how to obtain the representation vector of personality type based on the portrait data and historical behavior data will be discussed in the following section. Figure 4 The steps shown are described in detail and will not be repeated here to avoid repetition.

[0070] Step S23: Obtain a representation vector of each service content in the service content database.

[0071] In some embodiments of the present application, the characteristics of the service content include the category of the service content, the number of times the service content is triggered, and the group of people who trigger the service content.

[0072] In some embodiments of the present application, the service content may be feature encoded by methods such as One-Hot Encoding and Embedding to obtain a representation vector of the service content.

[0073] In some embodiments of the present application, it is also possible to digitize each feature in the service content based on feature vectorization technology, establish a trainable vector mapping table for the value of each feature, and use models such as neural networks to train these vectors to capture the potential relationship between features, thereby converting each feature of the service content into a representation vector. Specifically, each feature in the service content is represented by a number. For example, the category of the service content can be mapped to an integer starting from 0. Features that are not convenient to represent by numbers can be mapped to a value according to set rules. For example, different groups of people can be mapped to different numerical identifiers. For each feature in the service content, a mapping table of values ​​to vectors is established, in which the initial vector is a random value, and subsequent vectors can be trained through the back propagation algorithm of the neural network to obtain a representation vector mapping table for each feature, which can map feature values ​​to different representation vectors. Based on the representation vector mapping table of each feature of the service content, the representation vector of each feature of the service content is obtained, and the representation vector of each feature of the service content is aggregated to obtain the representation vector of the service content.

[0074] In some embodiments of the present application, the electronic device 10 may also obtain a representation vector of each service content based on a recurrent neural network (RNN) model.

[0075] Step S24, determining the service content corresponding to the personality type from the service content database.

[0076] It should be noted that how to determine the service content corresponding to the personality type from the service content database is described in detail in step S12 of the above embodiment, and will not be described again here to avoid repetition.

[0077] Step S25: Based on the trained matching model, a matching value between the representation vector of the personality type and the representation vector of each service content corresponding to the personality type is determined.

[0078] Specifically, the representation vector of the personality type and the representation vector of each service content corresponding to the personality type are concatenated together in pairs to form a longer input vector, which is input into the trained matching model. The matching value between the representation vector of the personality type and the representation vector of each service content corresponding to the personality type is calculated based on the trained matching model (for example, a matching value of 1 indicates a match, and a matching value of 0 indicates a mismatch).

[0079] Specifically, the training method of the matching model includes obtaining sample portrait data and / or sample behavior data of multiple users associated with each sample service content in the service content database and obtaining a representation vector for each sample service content; obtaining a representation vector for the sample personality type of each user based on the portrait data and / or behavior data of each user; obtaining a matching value label between the representation vector of the sample personality type of each user and the representation vector of each sample service content; establishing a training data set, the training data set including multiple training samples, each training sample including a representation vector of the sample personality type, a representation vector of the sample service content, and a matching value label between the representation vector of the sample personality type and the representation vector of the sample service content; and using the training data set to train the preset model to obtain a trained matching model.

[0080] It should be noted that the training method of the matching model will be discussed later. Figure 5 The steps shown are described in detail and will not be repeated here to avoid repetition.

[0081] In some embodiments of the present application, the electronic device 10 may also use a cosine similarity model, a twin tower model, a similarity model, etc. to calculate a matching value between a representation vector of a personality type and a representation vector of each service content corresponding to the personality type.

[0082] Step S26: The service content whose matching value is a preset value is used as the service content to be recommended.

[0083] Specifically, the matching value being a preset value indicates that the representation vector of the service content matches the representation vector of the personality type, and the service content with the matching value being the preset value is used as the service content to be recommended. The preset value can be set according to actual needs, for example, 1, and this application does not limit this.

[0084] Step S27: recommend the service content to be recommended to the user in voice form and / or visual form.

[0085] It should be noted that how to recommend the service content to be recommended to the user in voice form and / or visual form is described in detail in step S13 of the above embodiment, and will not be repeated here to avoid repetition.

[0086] In the method for actively recommending service content based on user personality in the above-mentioned embodiment, a representation vector of personality type is generated according to the user's portrait data and / or the user's historical behavior data, which can capture the slight personality differences between similar users, wherein the vector dimension can be manually adjusted, and the higher the dimension, the stronger the ability to represent slight differences between personalities. The vector embedding technology based on neural networks performs feature encoding on the user's personality type and each service content, and both are represented in the form of vectors, thereby expanding the richness of information representation. By calculating the matching value of the representation vector of the personality type and the representation vector of the service content, different content is actively recommended to users of different personality types, thereby improving the accuracy of the recommended content, being able to more accurately meet the personalized needs of different users, improving service efficiency, reducing manual intervention, and expanding the scope of recommendation, thus achieving active recommendation of services without disturbing users too much, thereby improving user experience.

[0087] See also Figure 4 , which is a schematic diagram of specific steps of step S22 in the method for actively recommending service content based on user personality provided in one embodiment of the present application.

[0088] This embodiment is a specific description of step S22 in the above embodiment, and further describes how to obtain a personality type representation vector based on the portrait data and historical behavior data. Specifically, the following steps are included: Step S220, obtaining the representation vector of the portrait data and the representation vector of the historical behavior data.

[0089] In some embodiments of the present application, the characteristics of the portrait data include age, gender, occupation, the frequency of use of each function of the voice assistant by the user, the model and price of the vehicle 1 purchased by the user, and other characteristics.

[0090] In some embodiments of the present application, the portrait data may be feature encoded by methods such as One-Hot Encoding and Embedding to obtain a representation vector of the portrait data.

[0091] In some embodiments of the present application, it is also possible to digitize each feature in the portrait data based on feature vectorization technology, establish a trainable vector mapping table for the value of each feature, and use models such as neural networks to train these vectors to capture the potential relationship between features, thereby converting each feature of the portrait data into a representation vector. Specifically, each feature in the portrait data is represented by a number. For example, an occupation can be mapped to an integer starting from 0. Features that are not convenient to represent by numbers can be mapped to a value according to set rules. For example, different car models can be mapped to different numerical identifiers. For each feature in the portrait data, a mapping table of values ​​to vectors is established, in which the initial vector is a random value, and subsequent vectors can be trained through the back propagation algorithm of the neural network to obtain a representation vector mapping table for each feature, which can map the feature value to different representation vectors. Based on the representation vector mapping table of each feature of the portrait data, the representation vector of each feature of the portrait data is obtained, and the representation vector of each feature of the portrait data is aggregated to obtain the representation vector of the portrait data.

[0092] In some embodiments of the present application, the electronic device 10 may obtain a representation vector of each portrait data based on a recurrent neural network (RNN) model.

[0093] In some embodiments of the present application, the behavior features of the historical behavior data include the action of each behavior and the scene entity corresponding to the action of each behavior. The data format of each behavior in the historical behavior data is converted into a structure of action+entity, such as navigation+shopping mall, navigation+entertainment venue, play+soothing music, etc.

[0094] In some embodiments of the present application, the historical behavior data may be feature encoded by methods such as One-Hot Encoding and Embedding to obtain a representation vector of the historical behavior data.

[0095] In some embodiments of the present application, it is also possible to digitize each feature in the historical behavior data based on feature vectorization technology, and establish a trainable vector mapping table for the value of each feature, and use models such as neural networks to train these vectors to capture the potential relationship between features, thereby converting each feature of the historical behavior data into a representation vector. Specifically, numbers can be assigned to different actions and scene entities, for example, navigating to a shopping mall can be represented as 0101, navigating to an entertainment venue can be represented as 0102, and playing soothing music can be represented as 0203. A mapping table of values ​​to vectors is established for each behavior feature in the historical behavior data, wherein the initial vector is a random value, and subsequent vectors can be trained through the back propagation algorithm of the neural network to obtain a representation vector mapping table for each behavior feature, which can map feature values ​​to different representation vectors. Based on the representation vector mapping table of each behavior feature of the historical behavior data, the representation vector of each behavior feature of the historical behavior data is obtained.

[0096] For the user's historical behavior data, since the user's behavior may be different over a period of time, the length of the representation vector of each behavior feature is inconsistent. Therefore, after the representation vector of each behavior feature, the representation vectors of all behavior features of the historical behavior data can be averaged, and the average of the representation vectors of all behavior features can be used as the representation vector of the historical behavior data.

[0097] Step S221, aggregate the representation vector of the portrait data and the representation vector of the historical behavior data to obtain the representation vector of the personality type.

[0098] In some embodiments of the present application, the aggregation of two representation vectors may be achieved by using a combination of one or more of the following methods: addition, concatenation, weighted sum, etc.

[0099] In another example of the present application, a neural network or other machine learning model can also be used to aggregate the two representation vectors. For example, a neural network including fully connected layers or an attention mechanism can be designed to process the two representation vectors and fuse the two representation vectors.

[0100] In the above embodiment, the vector embedding technology based on the neural network encodes the user's portrait data and historical behavior data to generate a vector representation, aggregates the representation vector of the portrait data and the representation vector of the historical behavior data as the representation vector of the user's personality type, expands the richness of the information representation, and can capture the slight personality differences between similar users. The vector dimension can be adjusted manually, and the higher the dimension, the stronger the ability to represent slight differences between personalities. When the user's recent behavior changes, the change in the user's behavior can be captured by identifying the difference in the representation vector of the user's historical behavior data, and then timely perceives whether the user's personality type has changed, effectively solving the problem of the user's personality type changing over time.

[0101] See also Figure 5 , is a schematic diagram of the specific steps of the training method of the matching model provided in one embodiment of the present application.

[0102] This embodiment is a specific description of the training method of the matching model in the above embodiment, and further describes the training method of the matching model. Specifically, it includes the following steps: Step S250, obtaining sample portrait data and / or sample behavior data of multiple users associated with each sample service content in the service content database, and obtaining a representation vector for each sample service content.

[0103] Specifically, the electronic device 10 may collect the portrait data and / or behavior data of multiple users associated with each service content from the service log of each service content.

[0104] It should be noted that how to obtain the representation vector of each sample service content is described in detail in step S23 of the above embodiment, and will not be described again here to avoid repetition.

[0105] Step S251, obtaining a representation vector of the sample personality type of each user based on the sample portrait data and / or sample behavior data of each user.

[0106] It should be noted that how to obtain the representation vector of the sample personality type of each user based on the sample portrait data and / or sample behavior data of each user is described in detail in step S22 of the above embodiment, and will not be repeated here to avoid repetition.

[0107] Step S252: Obtain a matching value label between the representation vector of each user's sample personality type and the representation vector of each sample service content.

[0108] In some embodiments of the present application, the matching value label between the sample personality type representation vector of each user and the sample service content representation vector of each user can be obtained by receiving the input of the user (e.g., expert user). The matching value label can be in binary form, that is, it only contains two possible values ​​(e.g., 0 and 1).

[0109] For example, if the matching value label of the representation vector of sample personality type A and the representation vector of sample service content B is a preset value (for example, 1), it means that the representation vector of sample personality type A and the representation vector of sample service content B are matched with each other, which means that sample service content B may be very suitable for users with sample personality type A.

[0110] If the matching value label of the representation vector of the sample personality type C and the representation vector of the sample service content D is another value (for example, 0), it indicates that the representation vector of the sample personality type C and the representation vector of the sample service content D do not match, which means that the sample service content D may not be suitable for users with the sample personality type C.

[0111] In the above embodiment, the matching value labels can clearly indicate which service content is more suitable for which personality type of users, and the model can be guided to use the matching value labels in the subsequent process to learn and understand the preferences and needs of users of different personality types for service content. On this basis, the model can further optimize its recommendation algorithm to ensure that each user is provided with more personalized recommended content or services that fit their personality characteristics.

[0112] Step S253: establishing a training data set, where the training data set includes a plurality of training samples.

[0113] Specifically, each training sample includes a representation vector of the sample personality type, a representation vector of the sample service content, and a matching value label between the representation vector of the sample personality type and the representation vector of the sample service content.

[0114] For example, a training sample can be represented as: {representation vector of sample personality type A; representation vector of sample service content B; matching value label 1 between the representation vector of sample personality type A and the representation vector of sample service content B}; another training sample can be represented as: {representation vector of sample personality type C; representation vector of sample service content D; matching value label 0 between the representation vector of sample personality type C and the representation vector of sample service content D}.

[0115] Step S254, using the training data set to train the preset model to obtain a trained matching model.

[0116] In some embodiments of the present application, the preset model may include but is not limited to a feedforward neural network (FNN) model, a convolutional neural network (CNN) model, a recurrent neural network (RNN) model, a deep structured semantic model (DSSM), etc. The model structure of the preset model can be selected according to actual needs, and the present application does not impose specific restrictions on this.

[0117] In some embodiments of the present application, when training a preset model, the training data can be input into the preset model in batches, and the preset model learns the potential relationship between the representation vector of the personality type and the representation vector of the service content, and how these relationships are associated with the matching value labels. Through continuous iteration and optimization, the preset model can gradually improve the accuracy of its prediction of the matching value labels between the representation vector of the personality type and the representation vector of the service content.

[0118] Among them, the prediction error of the preset model can be minimized and the generalization ability of the model can be improved by adjusting the internal parameters and structure of the preset model based on optimization methods such as gradient descent and back propagation. When the preset model reaches the preset training conditions on the training data set, it can be considered that the training is completed and the matching model is obtained. For example, the preset training conditions may include but are not limited to the training iteration reaching the preset number of iterations, the model prediction accuracy reaching the preset accuracy threshold, etc.

[0119] In the above implementation, the matching model obtained through the above training method not only has the ability to accurately predict the degree of matching between user personality and service content, but also can dynamically adjust its recommendation strategy according to new user data and service content, so as to continuously provide users with more accurate and personalized service experience and enhance the user experience.

[0120] See also Figure 6 , is a functional module diagram of a device 100 for actively recommending service content based on user personality provided in one embodiment of the present application.

[0121] In this embodiment, based on the above Figure 2The present application also provides a device 100 for actively recommending service content based on user personality, which is similar to the concept of the method for actively recommending service content based on user personality in the illustrated embodiment, and can be used to execute the method for actively recommending service content based on user personality. For ease of explanation, the schematic diagram of the embodiment of the device 100 for actively recommending service content based on user personality only shows the parts related to the embodiment of the present application. Those skilled in the art can understand that the schematic structure does not constitute a limitation on the device 100 for actively recommending service content based on user personality, and can include more or fewer components than those shown in the diagram, or combine certain components, or arrange the components differently.

[0122] Specifically, the device 100 for actively recommending service content based on user personality provided in the embodiment of the present application includes an acquisition module 110 , a first determination module 120 , a second determination module 130 , and a recommendation module 140 .

[0123] The acquisition module 110 is used to acquire comprehensive user data of the user.

[0124] In some embodiments of the present application, the user comprehensive data includes but is not limited to the user's portrait data and the user's historical behavior data. The portrait data includes but is not limited to the user's basic information (such as age, gender, occupation, etc.), the frequency of use of each function of the voice assistant (such as navigation function, entertainment function, calling function, etc.) by the user, and the model and price of the vehicle 1 purchased by the user.

[0125] The electronic device 10 may obtain the user's portrait data through user registration information, questionnaires, or third-party data providers.

[0126] In some embodiments of the present application, historical behavior data includes but is not limited to the historical interaction behavior between the user and the voice assistant (such as the conversation records between the user and the voice assistant, the user's specific commands to the voice assistant, etc.), the user's historical control behavior of using vehicle 1 (such as the user's control of service functions through the physical switches or virtual switches of vehicle 1, the time and frequency of the user's use of vehicle 1, etc.).

[0127] Among them, the physical switch of the vehicle 1 refers to a physical button, knob, switch, etc., and the virtual switch refers to a virtual button displayed on the touch screen.

[0128] The user's service function control behaviors through the physical switches or virtual switches of the vehicle 1 may include but are not limited to opening / closing windows, adjusting seats, etc.

[0129] The electronic device 10 may collect the user's historical behavior data from the historical service log of the vehicle 1 .

[0130] In some embodiments of the present application, the user comprehensive data may also include the user's historical voice data and the user's historical text data. Among them, the user's historical voice data includes but is not limited to the voice content and voice features (such as speech speed, pitch, volume, rhythm, emotion, etc.) of the user's interaction with the voice assistant. The user's historical text data includes but is not limited to query records, interactive texts, user feedback, etc. for the service content of vehicle 1. After the electronic device 10 obtains the voice content of the user's interaction with the voice assistant, it needs to convert the user's voice content into text data for subsequent analysis and processing.

[0131] It should be noted that the electronic device 10 strictly abides by the privacy protection policy to ensure that all data acquisition and processing are carried out within the scope of user consent and permitted by laws and regulations.

[0132] In some embodiments of the present application, after obtaining the user's comprehensive data, the electronic device 10 may also preprocess the user's comprehensive data. For example, the preprocessing may include but is not limited to cleaning and formatting operations, such as removing invalid or erroneous data entries, filling missing values, converting data formats, etc., to ensure the quality and consistency of the user's comprehensive data.

[0133] The first determination module 120 is used to determine the personality type of the user according to the comprehensive data of the user.

[0134] Specifically, the step of determining the user's personality type based on the user's comprehensive data specifically includes: performing a multi-dimensional personality analysis on the user based on the user's comprehensive data to obtain the user's multi-dimensional personality analysis results; based on the multi-dimensional personality analysis results, performing personality classification and matching on the user through a preset machine learning algorithm to determine the user's personality type.

[0135] Among them, based on psychological theories, such as the five personality trait models (such as openness, responsibility, extroversion, agreeableness, and neuroticism), the user's comprehensive data is analyzed to extract personality-related features. For example, the user's usage habits can be determined based on the frequency of use of each function of the voice assistant by the user; the user's interaction habits can be determined based on the user's interaction behavior with the voice assistant; the user's entertainment and life behaviors using the voice assistant can determine the user's behavioral habits. The extracted features are input into the machine learning algorithm (such as decision tree, support vector machine, neural network, etc.) to obtain the user's personality type, such as extroversion, introversion, rationality, emotionality, etc., and a personality profile containing a detailed description of the personality type is generated for each personality type.

[0136] The second determining module 120 is used to determine the service content to be recommended from a preset service content database based on the personality type.

[0137] Specifically, the preset service content database stores multiple service contents, including but not limited to voice services of a voice assistant (such as reminders, suggestions, greetings, etc.), entertainment services of vehicle 1 (such as playing music, playing news, etc.), control services of vehicle 1 (such as opening and closing windows, adjusting seats, etc.), etc.

[0138] Associate each service content with a personality type. For example, an "extrovert" user may prefer vibrant entertainment information. Based on the personality type, determine the service content corresponding to the personality type from the service content database as the service content to be recommended using a preset recommendation algorithm (such as collaborative filtering, content recommendation, hybrid recommendation, etc.).

[0139] The recommendation module 130 is used to recommend the service content to be recommended to the user in voice form and / or visual form.

[0140] In some embodiments of the present application, the service content to be recommended is converted into voice data based on a preset deep learning algorithm, the voice data is output through the speaker 20, and the service content to be recommended is provided to the user in voice form, thereby realizing active recommendation of service content to the user, which is particularly suitable for use in driving scenarios and can ensure driving safety.

[0141] In some embodiments of the present application, the electronic device 10 sends the content to be recommended to the display 30, displays the service content to be recommended through the display 30, and provides the service content to be recommended to the user in a visual form, thereby actively recommending service content to the user, making the interaction more natural and intuitive.

[0142] In the device 100 for actively recommending service content based on user personality in the above embodiment, in the method for actively recommending service content based on user personality in the above embodiment, personality analysis is performed using comprehensive user data, and different service content is recommended to users of different personality types, which provides deeper user insights, improves the accuracy of recommended content, and can more accurately meet the personalized needs of different users, improves the accuracy of service recommendations, and realizes active recommendation of services without disturbing users too much, thereby improving user experience. Actively recommending services to users based on their personality types improves service efficiency, and users can obtain the required information faster without waiting or performing additional operations, making it smoother and more convenient for users to use the service functions of the smart cockpit. Recommending recommended content to users in voice and / or visual form makes the interaction more natural and intuitive.

[0143] Combination Figure 1As shown, in some embodiments of the present application, the electronic device 10 includes, but is not limited to, a memory 11, a processor 12, and a computer program stored in the memory 11 and executable on the processor 12, such as a program for actively recommending service content based on user personality. When the computer program is executed by the processor, a method for actively recommending service content based on user personality as in the above-mentioned embodiment is implemented.

[0144] Figure 1 Only the electronic device 10 having the memory 11 and the processor 12 is shown, and those skilled in the art can understand that Figure 1 The structure shown does not constitute a limitation on the electronic device 10 , and the electronic device 10 may include fewer or more components than shown in the figure, or combine some components, or arrange the components differently.

[0145] The memory 11 in the electronic device 10 stores multiple computer-readable instructions to implement a method for actively recommending service content based on user personality. The processor 12 can execute multiple instructions to achieve: determining the user's personality type based on the user's comprehensive data; determining the service content to be recommended from a preset service content database based on the personality type; and recommending the service content to be recommended to the user in voice form and / or visual form.

[0146] Specifically, the specific implementation method of the processor 12 for the above instructions can refer to Figure 2 The description of the relevant steps in the corresponding embodiments will not be repeated here.

[0147] Those skilled in the art will appreciate that the schematic diagram is merely an example of the electronic device 10 and does not constitute a limitation on the electronic device 10. The electronic device 10 may be a bus-type structure or a star-type structure. The electronic device 10 may also include more or less other hardware or software than shown in the figure, or a different arrangement of components. For example, the electronic device 10 may also include input and output devices, network access devices, etc.

[0148] It should be noted that the electronic device 10 is only an example, and other existing or future electronic products that are suitable for the present application should also be included in the protection scope of the present application and included here by reference.

[0149] Among them, the memory 11 includes at least one type of computer-readable storage medium, and the computer-readable storage medium can be non-volatile or volatile. Computer-readable storage media include flash memory, mobile hard disk, multimedia card, card-type memory (such as SD memory, DX memory, etc.), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 11 can be an internal storage unit of the electronic device 10, such as a mobile hard disk of the electronic device 10. In other embodiments, the memory 11 can also be an external storage device of the electronic device 10, such as a plug-in mobile hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device 10. The memory 11 can not only be used to store application software installed in the electronic device 10 and various types of data, such as a code for a service content active recommendation program based on user personality, but also can be used to temporarily store data that has been output or is to be output.

[0150] In some embodiments, the processor 12 may be composed of an integrated circuit, for example, a single packaged integrated circuit, or a plurality of packaged integrated circuits with the same or different functions, including one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and a combination of various control chips. The processor 12 is the control core (Control Unit) of the electronic device 10, and uses various interfaces and lines to connect various components of the entire electronic device 10, and executes various functions and processes data of the electronic device 10 by running or executing programs or modules stored in the memory 11 (for example, executing a service content active recommendation program based on user personality, etc.), and calling data stored in the memory 11.

[0151] The processor 12 executes the operating system of the electronic device 10 and various installed applications. The processor 12 executes the application to implement the steps in the above-mentioned embodiment of the method for actively recommending service content based on user personality, for example Figure 2-Figure 5 Steps shown.

[0152] Exemplarily, the computer program may be divided into one or more modules / units, one or more modules / units are stored in the memory 11, and executed by the processor 12 to complete the present application. One or more modules / units may be a series of computer-readable instruction segments capable of completing specific functions, and the instruction segments are used to describe the execution process of the computer program in the electronic device 10. For example, the computer program may be divided into an acquisition module 110, a first determination module 120, a second determination module 130, and a recommendation module 140.

[0153] The above-mentioned integrated unit implemented in the form of a software function module can be stored in a computer-readable storage medium. The above-mentioned software function module is stored in a storage medium, and includes a number of instructions for enabling a computer device (which can be a personal computer, a computer device, or a network device, etc.) or a processor to execute a part of a method for actively recommending service content based on user personality in various embodiments of the present application.

[0154] If the module / unit integrated in the electronic device 10 is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, and can also instruct the relevant hardware devices to complete through a computer program. The computer program can be stored in a computer-readable storage medium, and when the computer program is executed by the processor, the steps of each of the above-mentioned method embodiments can be implemented.

[0155] The computer program includes computer program code, which may be in source code form, object code form, executable file or some intermediate form, etc. Computer readable media may include: any entity or device capable of carrying computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory and other memory, etc.

[0156] Furthermore, the computer-readable storage medium may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function, etc.; the data storage area may store data created according to the use of the blockchain node, etc.

[0157] The bus can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. Figure 1 Only one arrow is used in the figure, but it does not mean that there is only one bus or one type of bus. The bus is configured to realize the connection and communication between the memory 11 and at least one processor 12, etc.

[0158] An embodiment of the present application also provides a computer-readable storage medium (not shown), in which computer-readable storage medium is stored computer-readable instructions, and the computer-readable instructions are executed by a processor in the electronic device 10 to implement a method for actively recommending service content based on user personality in any of the above embodiments.

[0159] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of modules is only a logical function division, and there may be other division methods in actual implementation.

[0160] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0161] In addition, each functional module in each embodiment of the present application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The above integrated unit can be implemented in the form of hardware or in the form of hardware plus software functional modules.

[0162] In addition, it is obvious that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices stated in the specification can also be implemented by one unit or device through software or hardware. The words first, second, etc. are used to indicate names, and do not indicate any specific order.

[0163] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present application and are not intended to limit it. Although the present application has been described in detail with reference to the preferred embodiments, a person of ordinary skill in the art should understand that the technical solution of the present application may be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present application.

Claims

1. A method for actively recommending service content based on user personality, characterized in that: The method comprises: Obtain comprehensive user data of users; Determining the personality type of the user based on the comprehensive data of the user; Based on the personality type, determining the service content to be recommended from a preset service content database; The service content to be recommended is recommended to the user in voice form and / or visual form.

2. The method for actively recommending service content based on user personality as claimed in claim 1, characterized in that: The user comprehensive data includes the user's portrait data and / or the user's historical behavior data; Among them, the portrait data includes the basic information of the user, the frequency of use of each function of the voice assistant by the user, and the model and price of the vehicle purchased by the user; the historical behavior data includes the historical interaction behavior of the user with the voice assistant, and the historical control behavior of the user using the vehicle.

3. The method for actively recommending service content based on user personality as claimed in claim 2, characterized in that: The method further comprises: A representation vector of the personality type is obtained according to the portrait data and / or the historical behavior data.

4. The method for actively recommending service content based on user personality as claimed in claim 3, characterized in that: The method further comprises: Obtaining a representation vector of the portrait data and a representation vector of the historical behavior data; The representation vector of the personality type is obtained according to the representation vector of the portrait data and / or the representation vector of the historical behavior data.

5. The method for actively recommending service content based on user personality as claimed in claim 3, characterized in that: The method further comprises: A representation vector of each service content in the service content database is obtained.

6. The method for actively recommending service content based on user personality as claimed in claim 5, characterized in that: The method further comprises: Determining the service content corresponding to the personality type from the service content database; Determine, based on the trained matching model, a matching value between the representation vector of the personality type and the representation vector of each service content corresponding to the personality type; The service content whose matching value is a preset value is used as the service content to be recommended.

7. The method for actively recommending service content based on user personality as claimed in claim 6, characterized in that: The training method of the matching model includes: Acquire sample portrait data and / or sample behavior data of multiple users associated with each sample service content in the service content database, and acquire a representation vector of each sample service content; Obtaining a representation vector of the sample personality type of each user according to the sample portrait data and / or the sample behavior data of each user; Obtaining a matching value label between a representation vector of a sample personality type of each user and a representation vector of each sample service content; Establishing a training data set, the training data set comprising a plurality of training samples, each training sample comprising a representation vector of the sample personality type, a representation vector of the sample service content, and a matching value label between the representation vector of the sample personality type and the representation vector of the sample service content; The preset model is trained using the training data set to obtain the trained matching model.

8. The method for actively recommending service content based on user personality as claimed in claim 1, characterized in that: Determining the personality type of the user according to the comprehensive user data includes: Performing a multi-dimensional personality analysis on the user based on the user comprehensive data to obtain a multi-dimensional personality analysis result of the user; Based on the multi-dimensional personality analysis result, the personality classification and matching of the user is performed through a preset machine learning algorithm to determine the personality type of the user.

9. A device for actively recommending service content based on user personality, characterized in that: The device comprises: An acquisition module is used to acquire comprehensive user data of the user; A first determination module, used to determine the personality type of the user according to the comprehensive data of the user; A second determination module, configured to determine the service content to be recommended from a preset service content database based on the personality type; The recommendation module is used to recommend the service content to be recommended to the user in voice form and / or visual form.

10. An electronic device, characterized in that: The electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the computer program is executed by the processor, the method for actively recommending service content based on user personality as described in any one of claims 1 to 8 is implemented.

11. A vehicle, characterized in that: The vehicle includes the electronic device as claimed in claim 10.

Images