Information display method and system, electronic equipment and storage medium

Abstract

The invention discloses an information display method and system, electronic equipment and a storage medium, which are used for solving the problem of poor user experience in related information display technologies. The method comprises the steps of obtaining face features of a first user sent by a portable device, performing face feature comparison to obtain a face comparison result, and displaying first information of the first user on a display device according to the face comparison result; receiving dialogue voice data related to a first user in the current environment sent by the portable device; performing semantic analysis on the dialogue voice data through a pre-trained large language model to obtain a semantic analysis result; under the condition that it is determined that relevant information of the target user needs to be displayed on the basis of the semantic analysis result, first information of the target user is obtained, and to-be-displayed user information of the target user is generated through a large language model according to the semantic analysis result and the first information of the target user; and sending the to-be-displayed user information to a display device for display.

Description

Technical Field

[0001] This application belongs to the technical field of information display, and particularly relates to a method, a system, an electronic device, and a storage medium for information display. Background Art

[0002] In daily work and life, there is often a need to identify "who this person is" in real time. For example, at a social banquet, a guest is walking towards the user with a wine glass in hand, but the user can't remember who this guest is for a moment. If the greeting is inappropriate, it will be very embarrassing. Another example is that a delegation of dozens of people comes to the company for a visit. As the host, the user doesn't know everyone in the delegation. The user needs to introduce the company's situation to the delegation while paying attention to greeting each member. But if the user can't call out their names, it's also very embarrassing. For another example, when the police officers are patrolling on the street and a person passes by, the police officer feels that the person looks familiar and seems to be a wanted criminal, but can't remember for a moment.

[0003] In related information display technologies, the user issues a clear voice command to a mobile terminal such as a mobile phone, such as "Xiaoyi, help me check XXX", so that the mobile terminal queries and displays relevant information according to this voice command.

[0004] However, in the above-mentioned information display technology, the user needs to issue a voice command, which will cause embarrassment to the guests or alert the wanted criminal in the above scenarios, and then lead to embarrassing or dangerous situations for the user. That is, the related information display technology has the problem of poor user experience. Summary of the Invention

[0005] The embodiments of this application provide a method, a system, an electronic device, and a storage medium for information display, which can solve the problem of poor user experience in related information display technologies.

[0006] In a first aspect, the embodiments of this application provide a method for information display, which is applied to a cloud server. The method includes: obtaining the face features of a first user sent by a portable device, performing face feature comparison to obtain a face comparison result, and displaying the first information of the first user on a display device according to the face comparison result; receiving the dialogue voice data related to the first user in the current environment sent by the portable device; performing semantic analysis on the dialogue voice data through a pre-trained large language model to obtain a semantic analysis result; in the case where it is determined based on the semantic analysis result that the relevant information of the target user needs to be displayed, obtaining the first information of the target user, and generating the user information to be displayed of the target user through the large language model according to the semantic analysis result and the first information of the target user; sending the user information to be displayed to the display device for display.

[0007] Second aspect, an embodiment of the present application provides a display device for information, which is applied to a cloud server. The device includes: a first acquisition module, a second acquisition module, an analysis module, a generation module, and a sending module; the first acquisition module is configured to acquire the face features of a first user sent by a portable device, perform face feature comparison to obtain a face comparison result, and display the first information of the first user on a display device according to the face comparison result; the second acquisition module is configured to acquire the conversation voice data related to the first user in the current environment; the analysis module is configured to perform semantic analysis on the conversation voice data through a pre-trained large language model to obtain a semantic analysis result; the generation module is configured to, when it is determined based on the semantic analysis result that the relevant information of a target user needs to be displayed, acquire the first information of the target user, and generate the user information to be displayed of the target user through the large language model according to the semantic analysis result and the first information of the target user; the sending module is configured to send the user information to be displayed to the display device for display.

[0008] Third aspect, an embodiment of the present application provides a display system for information. The system includes a portable device, a cloud server, and a display device; the portable device is configured to acquire the face features of a first user and send the face features to the cloud server; and acquire the conversation voice data related to the first user in the current environment and send the conversation voice data to the cloud server; the cloud server is configured to: receive the face features sent by the portable device, perform face feature comparison to obtain a face comparison result, and send the first information of the first user to the display device according to the face comparison result; receive the semantic analysis result obtained by performing semantic analysis on the conversation voice data through a pre-trained large language model sent by the portable device; when it is determined based on the semantic analysis result that the relevant information of a target user needs to be displayed, acquire the first information of the target user, and generate the user information to be displayed of the target user through the large language model according to the semantic analysis result and the first information of the target user; send the user information to be displayed to the display device; the display device is configured to display the first information of the first user and the user information to be displayed of the target user.

[0009] Fourth aspect, an embodiment of the present application provides an electronic device. The electronic device includes: a processor; and a memory arranged to store computer-executable instructions, the executable instructions being configured to be executed by the processor, and the executable instructions include those for executing the information display method as described in the first aspect.

[0010] Fifth aspect, an embodiment of the present application provides a storage medium for storing computer-executable instructions that cause a computer to execute the information display method as described in the first aspect.

[0011] Sixth aspect, an embodiment of the present application provides a chip including a processor and a communication interface. The communication interface is coupled to the processor, and the processor is configured to run programs or instructions to implement the information display method as described in the first aspect.

[0012] Seventh aspect, an embodiment of the present application provides a computer program product including a computer program that, when executed by a processor, implements the information display method as described in the first aspect.

[0013] In an embodiment of the present application, by obtaining the face features of the first user sent by the portable device, performing face feature comparison to obtain a face comparison result, and based on the face comparison result, displaying the first information of the first user on the display device; receiving the dialogue voice data related to the first user in the current environment sent by the portable device; performing semantic analysis on the dialogue voice data through a pre-trained large language model to obtain a semantic analysis result; in the case where it is determined based on the semantic analysis result that the relevant information of the target user needs to be displayed, obtaining the first information of the target user, and generating the user information to be displayed of the target user by the large language model according to the semantic analysis result and the first information of the target user; sending the user information to be displayed to the display device for display. Compared with the related information display technology where the user must issue a voice command to provide information display, on the one hand, in the present application, by obtaining the face features of the first user sent by the portable device and performing face feature comparison, the first information of the first user can be displayed in real time without the user wearing the portable device issuing a voice command according to the face comparison result; on the other hand, by receiving the dialogue voice data related to the first user in the current environment sent by the portable device, the preset pre-trained large language model can perform semantic analysis on the dialogue voice data, and thus determine whether the relevant information of the target user needs to be displayed according to the semantic analysis result, and in the case where it is determined that the relevant information of the target user needs to be displayed, generate the user information to be displayed of the target user based on the semantic analysis result, so as to provide the relevant information of the target user that the user is concerned about to the user wearing the portable device when the user wearing the portable device does not issue a voice command and is talking with the first user; thereby, in scenarios such as banquet conversations, it avoids the embarrassment of guests and improves the user experience, solving the problem of poor user experience in the related information display technology. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1It is a schematic flowchart of a method for displaying information provided by an embodiment of the present application; Figure 2 It is a schematic flowchart of another method for displaying information provided by an embodiment of the present application; Figure 3 It is a schematic structural diagram of a device for displaying information provided by an embodiment of the present application; Figure 4(a) is a schematic structural diagram of a system for displaying information provided by an embodiment of the present application; Figure 4(b) is a schematic structural diagram of another system for displaying information provided by an embodiment of the present application; Figure 5 It is a schematic structural diagram of an electronic device provided by an embodiment of the present application. Detailed implementation manners

[0015] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

[0016] The terms "first", "second", etc. in the specification and claims of the present application are used to distinguish similar objects, rather than to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so that the embodiments of the present application can be implemented in an order other than those illustrated or described herein, and the objects distinguished by "first", "second", etc. are usually of the same category, and the number of objects is not limited. For example, the first object can be one or multiple. In addition, "and / or" in the specification and claims means at least one of the connected objects, and the character " / " generally represents an "or" relationship between the associated objects before and after.

[0017] Next, in conjunction with the accompanying drawings, the method, system, electronic device, and storage medium for displaying information provided by the embodiments of the present application will be described in detail through specific embodiments and their application scenarios.

[0018] Figure 1 An embodiment of the present invention provides a method for displaying information. This method can be executed by an electronic device, which may include: a cloud server. Among them, the cloud server can be a single server or a distributed server cluster composed of multiple servers, etc. In other words, this method can be executed by software or hardware installed in the electronic device. The method includes the following steps: S102: Obtain the facial features of the first user sent by the portable device, perform facial feature comparison to obtain a facial comparison result, and display the first information of the first user on the display device according to the facial comparison result.

[0019] Among them, the portable device can be a wearable portable device, which at least has the ability to collect the following dialogue voice data and facial images, such as augmented reality (AR) glasses, law enforcement recorders, etc. And the display device can be AR glasses, a mobile terminal (such as a mobile phone, etc.), and headphones, etc. Moreover, the display device can be one device or multiple devices. Therefore, the portable device and the display device can be the same device or not the same device, and no specific limitation is made in this regard.

[0020] The first user can be the user in front of the user wearing this portable device. Exemplarily, when the portable device is AR glasses, a guest is walking towards the user wearing the AR glasses with a wine glass in hand. If the user wearing this portable device wants to know the first information of the guest, then the guest is the first user.

[0021] Specifically, the portable device can collect the face image of the first user. After that, the feature extraction module extracts features from the face image to obtain face features. Among them, the feature extraction module can run as software on the portable device or as an independent hardware module, responsible for extracting the face features of the face image. The portable device can collect the face image of the first user and / or the following dialogue voice data when detecting the voice of the user wearing this portable device, in response to the triggering operation of the user wearing this portable device on the first preset button (such as the button of AR glasses) on the portable device, detecting the preset action of the user wearing this portable device, or detecting the user wearing this portable device using the preset wake-up word, etc. Among them, the triggering operation includes but is not limited to short pressing, long pressing, tapping or swiping, etc.; the preset action and wake-up word, etc. can be configured by default or customized by the user wearing this portable device according to actual needs, and no specific limitation is made thereto. Exemplarily, the portable device can be an AR glasses, and the user can tap the temple or frame of the AR glasses. In response to this tapping action of the user, the AR glasses start to collect the face image of the first user and / or the following dialogue voice data. It should be noted that this example does not limit the triggering conditions for the portable device to collect the face image of the first user and / or the following dialogue voice data. It should be understood that the portable device can also collect the face image in real time automatically without the above voice, triggering operation, preset action or preset wake-up word, etc. after the software of this application is started. When the face image is collected, the face features corresponding to the face image can be sent to the cloud server. When the cloud server obtains the face features sent by the portable device, it can perform face feature comparison in real time and automatically synchronize the first information corresponding to the face features of the user (i.e., the first information of the first user) to the display device.

[0022] In practical applications, the above cloud server can obtain the face features and the following dialogue voice data by connecting to the portable device in a wired or wireless manner. Considering that transmitting the face image of the first user may take a long time, therefore, directly transmitting the face features of the first user to the cloud server can effectively improve the real-time performance of finally displaying the first information of the first user on the display device, so as to realize the real-time display of the first information of the first user. Of course, the portable device can also send the face image of the first user while sending the face features of the first user.

[0023] The first information can include various types of information, including but not limited to one or more of the following: the face image of the user, the face features of the user, the name of the user, the profile of the user, the organization where the user is located (such as a company, a school), and the profile of the organization where the user is located, etc.

[0024] Optionally, the cloud server can send the first information of the first user to the portable device, and then send the first information of the first user to the display device through the portable device. The cloud server can also directly send the first information of the first user to the display device, so that the display device can display the first information of the first user to the user wearing this portable device in real time.

[0025] In addition, considering that due to the form of the first information storage, it is not convenient for users to understand the direct display. Therefore, before displaying on the display device, the first information of the first user can be processed by the pre-trained large language model in the following text to obtain the first information of the first user in the form of natural language, and then the first information of the first user in the form of natural language is sent to the display device. Exemplarily, the first information of the first user in the form of natural language: "The person in the photo is XXX. He is the founder of XXX Group. XXX Group is a XXX technology company, mainly engaged in e-commerce, Internet and technology businesses."

[0026] S104: Receive the conversation voice data related to the first user in the current environment sent by the portable device.

[0027] The conversation voice data can be the voice data of the user wearing this portable device and the first user in the current environment, etc., and no specific restrictions are imposed on this.

[0028] S106: Perform semantic analysis on the conversation voice data through the pre-trained large language model to obtain the semantic analysis result.

[0029] Among them, a pre-trained large language model is configured on the cloud server.

[0030] Specifically, there are at least two ways to perform semantic analysis on the conversation voice data through the pre-trained large language model: First, use the pre-trained speech recognition model to recognize the conversation voice data as text, and then the pre-trained large language model performs semantic analysis on the text to obtain the semantic analysis result; Second, use the pre-trained multimodal large model (Multimodal Large Language Model, MLLM) with speech understanding ability to directly perform semantic analysis on the conversation voice data to obtain the semantic analysis result. Among them, the pre-trained speech recognition model is trained based on the speech recognition model. Speech recognition models such as Whisper of OpenAI and SenseVoice of Alibaba Cloud. The pre-trained multimodal large model with speech understanding ability is trained based on the multimodal large model with speech understanding ability. Multimodal large models with speech understanding ability such as Google Gemini and Tencent VITA.

[0031] Among them, the semantic analysis result may include whether to display the relevant information of the target user, and in the case where the relevant information of the target user needs to be displayed, the relevant information that needs to be displayed of the target user. Specifically, the relevant information that needs to be displayed of the target user may be the information of the target user that the user wearing this portable device may be concerned about. Since the relevant information that needs to be displayed of the target user is related to the dialogue voice data, and the dialogue voice data is related to the dialogue scenario, different dialogue scenarios result in different dialogue voice data, and the information of the target user that the user wearing this portable device may be concerned about also varies accordingly, that is, the relevant information that needs to be displayed of the target user is different. In other words, the relevant information that needs to be displayed of the target user (semantic analysis result) is related to the dialogue scenario.

[0032] Exemplarily, the content of the dialogue voice data is: "First user: Did you see Li Hua the day before yesterday? How is he recently? User wearing this portable device: Oh, I haven't seen him for a long time. I heard last year that he went to XX Company." Through the aforementioned pre-trained large language model, semantic analysis is performed on the dialogue voice data, and the semantic analysis result is obtained: it is necessary to display the relevant information of "Li Hua", and the information of "Li Hua" that the user wearing this portable device may be concerned about: such as the position of "Li Hua" in "XX Company", etc.

[0033] It should be noted that the above example is only for facilitating the understanding of the semantic analysis result and does not limit the semantic analysis result.

[0034] Optionally, the pre-trained large language model may have the function of directly performing semantic analysis on the dialogue voice data. Correspondingly, the dialogue voice data can be directly input into the pre-trained large language model to achieve semantic analysis of the dialogue voice data; or a speech-to-text module can be configured to convert the dialogue voice data into a text-form dialogue, and then input the dialogue into the pre-trained large language model to enable the pre-trained large language model to perform semantic analysis on the dialogue voice data.

[0035] S108: In the case where it is determined based on the semantic analysis result that the relevant information of the target user needs to be displayed, obtain the first information of the target user, and generate the user information to be displayed of the target user through the large language model according to the semantic analysis result and the first information of the target user.

[0036] Specifically, through the large language model, the user information to be displayed is generated according to the relevant information that needs to be displayed of the target user and the first information in the semantic analysis result. Continuing with the above example, the user information to be displayed is the specific position of "Li Hua" in "XX Company", etc.

[0037] It can be understood that when the user wearing this portable device directly issues a voice command to the electronic device executing the solution of this application, the query of the user information to be displayed can also be realized. That is, the dialogue voice data can also be the voice command of the user wearing this portable device, such as "Xiaoa Xiaoa (example name), help me check XXX".

[0038] S110: Send the user information to be displayed to the display device for display.

[0039] Optionally, the user information to be displayed can be sent to the display device through the above-mentioned portable device, or the user information to be displayed can be directly sent to the display device, so that the display device can display the user information to be displayed to the user wearing this portable device in real time.

[0040] Among them, when the display device is a voice playback device such as an earphone, the display device can also be configured with a text-to-speech module to play the user information to be displayed and / or the first information of the above first user in the form of voice. In addition, when multiple display devices are set, the above-mentioned portable device can also be provided with an interaction module, and the interaction module can respond to the triggering operation of the user wearing this portable device on the preset second button on the portable device, and switch different display devices for display, such as the user information to be displayed and / or the first information of the above first user is displayed from the mobile terminal and becomes played by the earphone.

[0041] The information display method provided by the embodiments of the present invention obtains the face features of the first user sent by the portable device, performs face feature comparison to obtain a face comparison result, and displays the first information of the first user on the display device according to the face comparison result; receives the dialogue voice data related to the first user in the current environment sent by the portable device; performs semantic analysis on the dialogue voice data through a pre-trained large language model to obtain a semantic analysis result; in the case where it is determined based on the semantic analysis result that the relevant information of the target user needs to be displayed, obtains the first information of the target user, and generates the user information to be displayed of the target user through the large language model according to the semantic analysis result and the first information of the target user; sends the user information to be displayed to the display device for display. Compared with the related information display technology, where the user must issue a voice command to provide information display, on the one hand, the present application obtains the face features of the first user sent by the portable device and performs face feature comparison, so that the first information of the first user can be displayed in real time without the user wearing the portable device issuing a voice command according to the face comparison result; on the other hand, by receiving the dialogue voice data related to the first user in the current environment sent by the portable device, the preset pre-trained large language model can perform semantic analysis on the dialogue voice data, so as to determine whether the relevant information of the target user needs to be displayed according to the semantic analysis result, and in the case where it is determined that the relevant information of the target user needs to be displayed, generate the user information to be displayed of the target user based on the semantic analysis result, and further provide the relevant information of the target user concerned by the user wearing the portable device in the case where the user wearing the portable device does not issue a voice command and the user is talking with the first user; thus, in scenarios such as banquet conversations, it avoids the embarrassment of the guests, improves the user experience, and solves the problem of poor user experience in the related information display technology.

[0042] In one implementation, obtaining the face features of the first user sent by the portable device and performing face feature comparison to obtain a face comparison result (i.e., S102) can be specifically executed as steps A1 to A2 as follows: Step A1, obtain the face features of the first user sent by the portable device.

[0043] Step A2, based on the face features of the first user and the face features in the preset database, perform face feature comparison to obtain a face comparison result.

[0044] Wherein, if the face feature comparison is successful, the face comparison result includes the first information of the first user.

[0045] Specifically, the first information can be stored in the database in a form associated with other information in the face features.

[0046] In practical applications, a similarity algorithm can be preset. According to the preset similarity algorithm, the facial features of the first user are compared with the facial features in the preset database to obtain the first information corresponding to the facial features with a similarity greater than the preset threshold, that is, the facial feature comparison is successful, and the facial comparison result includes the first information of the first user.

[0047] In one implementation, the above semantic analysis result includes the second information in the dialogue voice data, and the second information represents the name of the target user. Obtaining the first information of the target user (i.e., S108) can be specifically executed as the following step B1: Step B1: Based on the second information, retrieve in the preset database to obtain the first information of the target user.

[0048] In practical applications, the second information can be the name of the target user or the alias of the target user (such as the internal alias used by some employees), etc. Continuing with the previous example, the second information can be "Li Hua".

[0049] Specifically, the first information can be stored in the database in the form of an association between the second information and other information in the first information. Considering the existence of homophones, first convert the second information into pinyin, and then retrieve in the database according to the pinyin to obtain the first information of the target user.

[0050] In addition, the facial features of the target user sent by the portable device can also be obtained. Then, based on the facial features of the target user and the second information, the first information of the target user is determined in the preset database.

[0051] In one implementation, the following steps C1 to C3 can also be executed to update the new first information to the database: Step C1: If the first information of the target user is not obtained, the large language model generates an introduction dialogue for the second information in the dialogue voice data according to the preset first prompt word and the dialogue voice data.

[0052] Among them, the first prompt word is used to enable the large language model to determine the introduction dialogue.

[0053] Step C2: Extract the introduction dialogue according to the information category corresponding to the first information in the database to generate introduction information.

[0054] Among them, the information category corresponding to the first information, such as the name of the user, the profile of the user, the organization where the user is located (such as a company, a school), the profile of the organization where the user is located, etc., is not specifically limited here. All the content belonging to the above information categories in the extracted introduction dialogue is generated as introduction information.

[0055] Step C3: Generate new first information based on the introduction information and the facial features of the corresponding first time period of the obtained introduction conversation, and update the database based on the new first information.

[0056] Specifically, the first information in the above database can include, but is not limited to, information obtained from one or more of the following sources: information publicly disclosed by some users on social media, ID photos, names, resumes, etc. publicly available on government websites, customer photos, visiting videos, etc. already saved in the Customer Relationship Management System (CRM).

[0057] Exemplarily, User A is the user wearing this portable device and is also the host of a certain banquet. User B and User C are guests. Among them, User A and User B already know each other, but User A does not know User C. In terms of social etiquette, after User B arrives, User B will introduce User C to User A. When the portable device hears the conversation in which User B introduces User C to User A, the portable device automatically uploads the captured facial features (or also includes facial images) of User C to this electronic device. In step A2, in the database, if the facial feature comparison of User C fails (for example, the similarity between the facial features of User C and the facial features in the database is less than the preset threshold), it is determined that there is no first information of User C in the database. Therefore, by using the above steps C1 to C3, the first information of User C (i.e., the new first information) is determined, and the database is updated based on the new first information. In addition, considering that the user wearing this portable device may look for User C when User B introduces User C, and in this process, the facial features (or also includes facial images) of other people are introduced, so the second time period can also be determined based on the first time period and the preset duration, and the facial features (or also includes facial images) of the corresponding user in the second time period are determined, and the facial features of the users already existing in the database are removed from the facial features of the corresponding user in the first time period to obtain the target facial features; then, based on the target facial features, the facial features of the corresponding user in the second time period (as candidates), and the introduction information, the new first information is generated, so that after the reviewer reviews the new first information, the reviewed first information is obtained, and thus the reviewed first information is updated to the database; where the second time period is a time period whose start time is before the start time of the first time period and whose end time is after the end time of the first time period. Among them, it can also be set that the CRM system where the user wearing this portable device is located is synchronized with this database, so that after the new first information is generated in the CRM system, a message can be sent to the salesperson, customer manager, etc. (i.e., the reviewer) who are connected with the customer in the CRM system, so that the reviewer can mark and proofread in time, and thus the database can be updated in time, which is convenient for the user wearing this portable device to use the first information subsequently.

[0058] In this embodiment, when the first information of the target user is not obtained, based on the large language model, new first information is automatically generated to update the database in a timely manner, facilitating the subsequent use by the user wearing this portable device.

[0059] In one implementation, retrieving in the preset database to obtain the first information of the target user (i.e., step B1) can be specifically executed as steps D1 to D2: Step D1, if the first information of multiple second users is retrieved in the database, then based on the preset second prompt word and the dialogue voice data through the large language model, determine the second user corresponding to the first information with the highest relevance to the dialogue voice data.

[0060] Among them, the second prompt word is used to enable the large language model to determine the second user corresponding to the first information with the highest relevance to the dialogue voice data.

[0061] Step D2, based on the second user corresponding to the first information with the highest relevance to the dialogue voice data, sort the first information of multiple second users to obtain the first information of the target user.

[0062] Exemplarily, if 2 "Li Hua" and 1 "Li Hua" are retrieved in the database. Then, through the large language model, it is determined that one of the "Li Hua" has the work experience in XX Company mentioned in the dialogue voice data. Then this "Li Hua" is the second user corresponding to the first information with the highest relevance to the dialogue voice data. The first information of the target user is: the first information with "Li Hua" who has the work experience in XX Company (the company mentioned in the dialogue voice data) at the head of the queue, and the first information of the subsequent "Li Hua" and 1 "Li Hua" can be arranged in sequence.

[0063] In one implementation, through the pre-trained large language model, semantic analysis is performed on the dialogue voice data to obtain the semantic analysis result (i.e., S106), which can be specifically executed as the following step E1: Step E1, input the preset third prompt word and the dialogue voice data into the large language model, and the large language model outputs the semantic analysis result.

[0064] Among them, the third prompt word is used to enable the large language model to determine whether there is a second information in the dialogue voice data, and in the case of the existence of the second information, output the second information and the relevant information that the target user needs to display; the second information represents the name of the target user.

[0065] Exemplarily, the third prompt word can be "Does this dialogue involve a person's name? If so, please extract the person's name and analyze what user information about this person the user wearing this portable device may be concerned about in this dialogue."

[0066] In one implementation, the following steps F1 to F4 can also be executed to give a prompt when a specific user exists around the user wearing this portable device: Step F1, obtain the facial features of a third user.

[0067] Among them, the third user and the above-mentioned second user and first user can be the same user or different users.

[0068] Step F2, based on the facial features of the third user and the facial features in the preset second database, perform facial comparison.

[0069] Among them, for the sake of distinction, the database that stores the first information before this embodiment can be called the first database, and the database in this embodiment is called the second database.

[0070] If the facial feature comparison is successful, the third information of the third user is included in the second facial comparison result.

[0071] Step F3, if the third information of the third user is included in the obtained second facial comparison result, then through a large language model, according to the third information of the third user and the preset fourth prompt word, generate an alarm message.

[0072] Among them, the fourth prompt word is used to enable the large language model to determine the alarm information related to the third information of the third user. This alarm information can be information in the form of natural language and related to the third information. Specifically, the third information stored in this second database can be determined based on the wanted notices issued by the police on the Internet, including but not limited to: the facial features, facial images of the people in the wanted notice and their corresponding introduction information, etc.

[0073] Step F4, send the alarm message to a display device for display.

[0074] Exemplarily, a police officer wears a law enforcement recorder, which collects the facial features of the people around. Through the cloud server, based on these facial features and the facial features in the preset second database, facial comparison is performed. If the third information of the third user is included in the obtained second facial comparison result, that is, when a wanted criminal is found, an alarm message can be immediately sent to the display device of the police officer. The display device can also be set to emit a sound and light alarm in response to the received alarm message. When the police officer takes out the display device, the relevant information (alarm message) of the wanted criminal can be seen on the display device.

[0075] Figure 2 It is a schematic flowchart of another information display method provided by an embodiment of the present application. As Figure 2 shown, this method includes: Step 202, obtain the face features of the first user sent by the portable device.

[0076] Step 204, perform face feature comparison based on the face features of the first user and the face features in the preset database to obtain a face comparison result.

[0077] Among them, if the face feature comparison is successful, the face comparison result includes the first information of the first user.

[0078] Step 206, display the first information of the first user on the display device according to the face comparison result.

[0079] Step 208, receive the dialogue voice data related to the first user in the current environment sent by the portable device.

[0080] Step 210, input the preset third prompt word and the dialogue voice data into the large language model, and the large language model outputs a semantic analysis result.

[0081] Among them, the third prompt word is used to enable the large language model to determine whether there is a second information in the dialogue voice data, and in the case of the existence of the second information, output the second information and the relevant information that the target user needs to display; the second information represents the name of the target user.

[0082] Step 212, in the case of determining that the relevant information of the target user needs to be displayed based on the semantic analysis result, retrieve in the preset database based on the second information to obtain the first information of the target user.

[0083] Step 214, generate the user information to be displayed of the target user by the large language model according to the semantic analysis result and the first information of the target user.

[0084] Step 216, send the user information to be displayed to the display device for display.

[0085] The specific processes of the above steps 202 to 216 have been described in detail in the above embodiments, and will not be elaborated here.

[0086] In this embodiment, the face features of the first user sent by the portable device are obtained, face feature comparison is performed to obtain a face comparison result, and according to the face comparison result, the first information of the first user is displayed on the display device; the conversation voice data related to the first user in the current environment sent by the portable device is received; through a pre-trained large language model, semantic analysis is performed on the conversation voice data to obtain a semantic analysis result; in the case where it is determined based on the semantic analysis result that the relevant information of the target user needs to be displayed, the first information of the target user is obtained, and the large language model generates the user information to be displayed of the target user according to the semantic analysis result and the first information of the target user; the user information to be displayed is sent to the display device for display. Compared with the related information display technology, the user must issue a voice command to provide information display. On the one hand, in this application, the face features of the first user sent by the portable device are obtained and face feature comparison is performed, so that the first information of the first user can be displayed in real time according to the face comparison result without the user wearing this portable device issuing a voice command. On the other hand, by receiving the conversation voice data related to the first user in the current environment sent by the portable device, the preset pre-trained large language model can perform semantic analysis on this conversation voice data, so as to determine whether the relevant information of the target user needs to be displayed according to the semantic analysis result, and in the case where it is determined that the relevant information of the target user needs to be displayed, based on the semantic analysis result, generate the user information to be displayed of the target user, and then can provide the relevant information of the target user concerned by the user wearing this portable device when the user wearing this portable device does not issue a voice command and the user is talking with the first user; thus, in scenarios such as banquet conversations, the embarrassment of guests is avoided, the user experience is improved, and the problem of poor user experience existing in the related information display technology is solved.

[0087] Corresponding to the information display method provided in the above embodiment, based on the same technical concept, an embodiment of the present invention also provides an information display device, Figure 3 which is a schematic structural diagram of the information display device according to an embodiment of the present invention. This information display device is used to execute Figures 1 to 2 the information display method described, as Figure 3 shown, the information display device includes: a first acquisition module 310, a second acquisition module 320, an analysis module 330, a generation module 340, and a sending module 350.

[0088] The first acquisition module 310 is configured to acquire the face features of the first user sent by the portable device, perform face feature comparison to obtain a face comparison result, and according to the face comparison result, display the first information of the first user on the display device.

[0089] The second acquisition module 320 is configured to acquire the dialogue voice data related to the first user in the current environment.

[0090] The analysis module 330 is configured to perform semantic analysis on the dialogue voice data through a pre-trained large language model to obtain a semantic analysis result.

[0091] The generation module 340 is configured to, when it is determined based on the semantic analysis result that the relevant information of the target user needs to be displayed, acquire the first information of the target user, and generate the user information to be displayed of the target user through the large language model according to the semantic analysis result and the first information of the target user.

[0092] The sending module 350 is configured to send the user information to be displayed to a display device for display.

[0093] In one implementation, the first acquisition module 310 is specifically configured to: Acquire the face features of the first user sent by the portable device; Perform face feature comparison based on the face features of the first user and the face features in the preset database to obtain a face comparison result; wherein, if the face feature comparison is successful, the face comparison result includes the first information of the first user.

[0094] In one implementation, the above semantic analysis result includes the second information in the dialogue voice data, and the second information represents the name of the target user. The generation module 340 includes a retrieval unit. The retrieval unit is specifically configured to: Retrieve in the preset database based on the second information to obtain the first information of the target user.

[0095] In one implementation, the above information display device further includes an update module. The update module is configured to: If the first information of the target user is not acquired, generate an introduction dialogue for the second information in the dialogue voice data through the large language model according to the preset first prompt word and the dialogue voice data; wherein the first prompt word is used to enable the large language model to determine the introduction dialogue; Extract the introduction dialogue according to the information category corresponding to the first information in the database to generate introduction information; Generate new first information based on the introduction information and the face features in the first time period corresponding to the acquired introduction dialogue, so as to update the database based on the new first information.

[0096] In one implementation, the above retrieval unit is specifically configured to: If multiple first pieces of information of the second users are retrieved from the database, the large language model is used to determine the second user corresponding to the first piece of information with the highest relevance to the conversation voice data according to the preset second prompt word and the conversation voice data; wherein, the second prompt word is used to enable the large language model to determine the second user corresponding to the first piece of information with the highest relevance to the conversation voice data. Based on the second user corresponding to the first piece of information with the highest relevance to the conversation voice data, the first piece of information of the target user is obtained by sorting the first pieces of information of the multiple second users.

[0097] In one implementation manner, the above analysis module 330 is specifically configured to: Input the preset third prompt word and the conversation voice data into the large language model, and the large language model outputs a semantic analysis result; wherein, the third prompt word is used to enable the large language model to determine whether there is a second piece of information in the conversation voice data, and in the case of the existence of the second piece of information, output the second piece of information and the relevant information to be displayed by the target user; the second piece of information represents the name of the target user.

[0098] Those skilled in the art should understand that the above information display device can be used to implement the foregoing information display method, and the detailed description thereof should be similar to the description in the foregoing method part. To avoid repetition, it will not be elaborated here.

[0099] In this embodiment, the face features of the first user sent by the portable device are obtained, face feature comparison is performed to obtain a face comparison result, and according to the face comparison result, the first information of the first user is displayed on the display device; the dialogue voice data related to the first user in the current environment sent by the portable device is received; through a pre-trained large language model, semantic analysis is performed on the dialogue voice data to obtain a semantic analysis result; in the case where it is determined based on the semantic analysis result that the relevant information of the target user needs to be displayed, the first information of the target user is obtained, and the large language model generates the user information to be displayed of the target user according to the semantic analysis result and the first information of the target user; the user information to be displayed is sent to the display device for display. Compared with the related information display technology, the user must issue a voice command to provide information display. On the one hand, in this application, by obtaining the face features of the first user sent by the portable device and performing face feature comparison, the first information of the first user can be displayed in real time without the user wearing this portable device issuing a voice command according to the face comparison result; on the other hand, by receiving the dialogue voice data related to the first user in the current environment sent by the portable device, the preset pre-trained large language model can perform semantic analysis on the dialogue voice data, so as to determine whether the relevant information of the target user needs to be displayed according to the semantic analysis result, and in the case where it is determined that the relevant information of the target user needs to be displayed, based on the semantic analysis result, generate the user information to be displayed of the target user, and then be able to provide the relevant information of the target user concerned by the user wearing this portable device when the user wearing this portable device does not issue a voice command and is talking with the first user; thus, in scenarios such as banquet conversations, the embarrassment of the guests is avoided, the user experience is improved, and the problem of poor user experience existing in the related information display technology is solved.

[0100] Based on the same technical concept, an embodiment of the present application also provides an information display system. FIG. 4 is a schematic structural diagram of the information display system according to an embodiment of the present invention. This system is used to execute the above information display method. As shown in FIGS. 4(a) and 4(b), the information display system includes: a portable device 410, a cloud server 420, and a display device 430.

[0101] The portable device 410 is used to obtain the face features of the first user and send the face features to the cloud server 420; and obtain the dialogue voice data related to the first user in the current environment and send the dialogue voice data to the cloud server 420.

[0102] The cloud server 420 is used for: Receive the face features sent by the portable device, perform face feature comparison to obtain a face comparison result, and send the first information of the first user to the display device 430 according to the face comparison result; Receive the semantic analysis result obtained by performing semantic analysis on the dialogue voice data through a pre-trained large language model sent by the portable device; In the case where it is determined based on the semantic analysis result that the relevant information of the target user needs to be displayed, obtain the first information of the target user, and generate the user information to be displayed of the target user through the large language model according to the semantic analysis result and the first information of the target user; Send the user information to be displayed to the display device 430.

[0103] The display device 430 is used to display the first information of the first user and the user information to be displayed of the target user.

[0104] Among them, for the information display system shown in Figure 4(a), both the first information of the first user and the user information to be displayed of the target user are sent by the cloud server 420 to the display device 430 through the portable device 410; for the information display system shown in Figure 4(b), both the first information of the first user and the user information to be displayed of the target user are sent directly by the cloud server 420 to the display device 430.

[0105] In one implementation, the portable device 410 is specifically used for: Collect a face image through a preset video capture module; Specifically, the video capture module can be responsible for collecting the picture that the user currently sees.

[0106] Extract features from the face image through a preset feature extraction module to obtain face features.

[0107] Optionally, the face feature extraction module can be set as software in the portable device 410, or can be used as an independent hardware to extract and process the face image to obtain the face features.

[0108] In one implementation, the cloud server 420 is specifically used for: Obtain the face features of the first user sent by the portable device; Based on the face features of the first user and the face features in the preset database, perform face feature comparison to obtain a face comparison result; among them, if the face feature comparison is successful, the face comparison result includes the first information of the first user.

[0109] In one implementation, the above semantic analysis result includes the second information in the dialogue voice data, and the second information represents the name of the target user. The cloud server 420 is specifically used for: Retrieve in a preset database based on the second information to obtain the first information of the target user.

[0110] In one implementation, the cloud server 420 is further configured to: If the first information of the target user is not obtained, generate an introduction dialogue for the second information in the dialogue voice data through a large language model according to a preset first prompt word; wherein, the first prompt word is used to enable the large language model to determine the introduction dialogue; Extract the introduction dialogue according to the information category corresponding to the first information in the database to generate introduction information; Generate new first information based on the introduction information and the face features of the first time period corresponding to the obtained introduction dialogue, and update the database based on the new first information.

[0111] In one implementation, the cloud server 420 is specifically configured to: If the first information of multiple second users is retrieved in the database, determine the second user corresponding to the first information with the highest relevance to the dialogue voice data through a large language model according to a preset second prompt word; wherein, the second prompt word is used to enable the large language model to determine the second user corresponding to the first information with the highest relevance to the dialogue voice data; Based on the second user corresponding to the first information with the highest relevance to the dialogue voice data, obtain the first information of the target user by sorting the first information of multiple second users.

[0112] In one implementation, the cloud server 420 is specifically configured to: Input a preset third prompt word and the dialogue voice data into the large language model, and the large language model outputs a semantic analysis result; wherein, the third prompt word is used to enable the large language model to determine whether there is second information in the dialogue voice data, and in the case of the existence of second information, output the second information and the relevant information that the target user needs to display; the second information represents the name of the target user.

[0113] The specific execution steps can refer to the respective steps of the display method embodiment of the above information, and can achieve the same technical effects. To avoid repetition, it will not be elaborated here.

[0114] It should be noted that the pre-trained large language model can also be set on the portable device 410. Then, the steps of using the pre-trained large language model are executed by the portable device 410, and the data transmission between the portable device 410 and the pre-trained large language model is changed from external transmission to internal transmission, while the other functions of the portable device 410, the cloud server 420, and the display device 430 are the same as those in the above embodiments.

[0115] In this embodiment, by obtaining the facial features of the first user sent by the portable device, performing facial feature comparison to obtain a facial comparison result, and based on the facial comparison result, displaying the first information of the first user on the display device; receiving the dialogue voice data related to the first user in the current environment sent by the portable device; performing semantic analysis on the dialogue voice data through a pre-trained large language model to obtain a semantic analysis result; in the case where it is determined based on the semantic analysis result that the relevant information of the target user needs to be displayed, obtaining the first information of the target user, and generating the user information to be displayed of the target user by the large language model according to the semantic analysis result and the first information of the target user; sending the user information to be displayed to the display device for display. Compared with the related information display technology, it is necessary for the user to issue a voice command to provide information display. On the one hand, in this application, by obtaining the facial features of the first user sent by the portable device and performing facial feature comparison, the first information of the first user can be displayed in real time without the user wearing this portable device issuing a voice command according to the facial comparison result. On the other hand, by receiving the dialogue voice data related to the first user in the current environment sent by the portable device, the preset pre-trained large language model can perform semantic analysis on the dialogue voice data, so as to determine whether the relevant information of the target user needs to be displayed according to the semantic analysis result, and in the case where it is determined that the relevant information of the target user needs to be displayed, based on the semantic analysis result, generate the user information to be displayed of the target user, and then be able to provide the relevant information of the target user concerned by the user wearing this portable device in the case where the user wearing this portable device does not issue a voice command and the user is talking with the first user; thus, in scenarios such as banquet conversations, the embarrassment of the guests is avoided, the user experience is improved, and the problem of poor user experience existing in the related information display technology is solved.

[0116] Based on the same technical concept, an embodiment of the present application also provides an electronic device, which is used to execute the above information display method. Figure 5 The structural schematic diagram of an electronic device for implementing each embodiment of the present application. The electronic device may vary greatly due to configuration or performance differences, and may include a processor 510, a communication interface 520, a memory 530, and a communication bus 540. Among them, the processor 510, the communication interface 520, and the memory 530 complete mutual communication through the communication bus 540. The processor 510 can call a computer program stored in the memory 530 and executable on the processor 510 to execute the following steps: Obtain the facial features of the first user sent by the portable device, perform facial feature comparison to obtain a facial comparison result, and display the first information of the first user on the display device according to the facial comparison result; Receive the conversation voice data related to the first user in the current environment sent by the portable device; Perform semantic analysis on the conversation voice data through a pre-trained large language model to obtain a semantic analysis result; When it is determined based on the semantic analysis result that the relevant information of the target user needs to be displayed, obtain the first information of the target user, and generate the user information to be displayed of the target user through the large language model according to the semantic analysis result and the first information of the target user; Send the user information to be displayed to the display device for display.

[0117] In this embodiment, by obtaining the facial features of the first user sent by the portable device, performing facial feature comparison to obtain a facial comparison result, and displaying the first information of the first user on the display device according to the facial comparison result; receiving the conversation voice data related to the first user in the current environment sent by the portable device; performing semantic analysis on the conversation voice data through a pre-trained large language model to obtain a semantic analysis result; when it is determined based on the semantic analysis result that the relevant information of the target user needs to be displayed, obtaining the first information of the target user, and generating the user information to be displayed of the target user through the large language model according to the semantic analysis result and the first information of the target user; sending the user information to be displayed to the display device for display. Compared with the related information display technology, it is necessary for the user to issue a voice command to provide information display. On the one hand, in this application, by obtaining the facial features of the first user sent by the portable device and performing facial feature comparison, the first information of the first user can be displayed in real time without the user wearing this portable device issuing a voice command according to the facial comparison result; on the other hand, by receiving the conversation voice data related to the first user in the current environment sent by the portable device, the preset pre-trained large language model can perform semantic analysis on the conversation voice data, so as to determine whether the relevant information of the target user needs to be displayed according to the semantic analysis result, and when it is determined that the relevant information of the target user needs to be displayed, generate the user information to be displayed of the target user based on the semantic analysis result, so that the relevant information of the target user that the user is concerned about can be provided to the user wearing this portable device when the user wearing this portable device does not issue a voice command and the user is talking with the first user; thus, in scenarios such as banquet conversations, the embarrassment of guests is avoided, the user experience is improved, and the problem of poor user experience in the related information display technology is solved.

[0118] The specific implementation steps can refer to the steps in the embodiments of the above information display method, and the same technical effects can be achieved. To avoid repetition, they will not be elaborated here.

[0119] It should be noted that the electronic devices in the embodiments of the present application include: servers, terminals, or other devices other than terminals.

[0120] The above structure of the electronic device does not limit the electronic device. The electronic device may include more or fewer components than shown in the figure, or combine certain components, or have different component arrangements. For example, the input unit may include a Graphics Processing Unit (GPU) and a microphone, and the display unit may be configured with a display panel in the form of a liquid crystal display, an organic light-emitting diode, etc. The user input unit includes at least one of a touch panel and other input devices. The touch panel is also called a touch screen. Other input devices may include, but are not limited to, a physical keyboard, function keys (such as volume control keys, switch keys, etc.), a trackball, a mouse, a joystick, which will not be elaborated here.

[0121] The memory can be used to store software programs and various data. The memory mainly includes a first storage area for storing programs or instructions and a second storage area for storing data. Among them, the first storage area can store an operating system, application programs or instructions required for at least one function (such as a sound playback function, an image playback function, etc.). In addition, the memory can include volatile memory or non-volatile memory, or the memory can include both volatile and non-volatile memory. Among them, the non-volatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory can be a random access memory (RAM), a static random access memory (SRAM), a dynamic random access memory (DRAM), a synchronous dynamic random access memory (SDRAM), a double data rate synchronous dynamic random access memory (DDR SDRAM), an enhanced synchronous dynamic random access memory (ESDRAM), a synchlink dynamic random access memory (SLDRAM), and a direct rambus random access memory (DRRAM).

[0122] The processor can include one or more processing units; optionally, the processor integrates an application processor and a modem processor. Among them, the application processor mainly processes operations related to the operating system, user interface, and application programs, etc., and the modem processor mainly processes wireless communication signals, such as a baseband processor. It can be understood that the above-mentioned modem processor may not be integrated into the processor either.

[0123] The embodiments of the present application also provide a storage medium, on which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, the embodiments of the above information display method are implemented, and the same technical effects can be achieved. To avoid repetition, details are not described here again.

[0124] Among them, the processor is the processor in the electronic device described in the above embodiments. The storage medium includes a computer-readable storage medium, such as a computer read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disc, etc.

[0125] Another embodiment of the present application provides a chip, which includes a processor and a communication interface. The communication interface is coupled to the processor. The processor is used to run programs or instructions to implement each process of the above embodiment of the information display method, and can achieve the same technical effect. To avoid repetition, it will not be elaborated here.

[0126] It should be understood that the chip mentioned in the embodiments of the present application may also be referred to as a system-on-chip, a system chip, a chip system, or a system-on-chip, etc.

[0127] The embodiments of the present application also provide a computer program product, including a computer program. When the computer program is executed by a processor, it implements each process of the above embodiment of the information display method, and can achieve the same technical effect. To avoid repetition, it will not be elaborated here.

[0128] It should be noted that in this article, the term "including", "comprising", or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article, or device including a series of elements not only includes those elements, but also includes other elements not explicitly listed, or further includes elements inherent to such process, method, article, or device. Without further limitations, an element defined by the statement "including a..." does not exclude the existence of additional identical elements in the process, method, article, or device including the element. In addition, it should be pointed out that the scope of the methods and devices in the embodiments of the present application is not limited to performing functions in the order shown or discussed. It may also include multitasking and parallel processing according to the functions involved, and various steps may be added, omitted, or combined. In addition, the features described with reference to certain examples may be combined in other examples.

[0129] Through the description of the above embodiments, those skilled in the art can clearly understand that the above-described embodiment methods can be implemented by means of software plus a necessary general hardware platform. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation. Based on such an understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions for causing a terminal (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in various embodiments of the present application.

[0130] The embodiments of the present application have been described above in conjunction with the accompanying drawings. However, the present application is not limited to the above specific implementation manners. The above specific implementation manners are merely illustrative rather than restrictive. Under the inspiration of the present application, those of ordinary skill in the art can also make many forms without departing from the purpose of the present application and the scope protected by the claims, and all of them fall within the protection scope of the present application.

Claims

1. A method for displaying information, characterized in that: Applied to a cloud server, the method includes: Acquire facial features of a first user sent by a portable device, perform facial feature comparison, obtain a facial comparison result, and display first information of the first user on a display device according to the facial comparison result; receiving conversation voice data related to a first user in a current environment sent by the portable device; Performing semantic analysis on the conversation speech data by using a pre-trained large language model to obtain a semantic analysis result; In a case where it is determined based on the semantic analysis result that relevant information of the target user needs to be displayed, first information of the target user is acquired, and user information to be displayed of the target user is generated by the large language model according to the semantic analysis result and the first information of the target user; The user information to be displayed is sent to the display device for display.

2. The method according to claim 1, characterized in that The acquiring the facial features of the first user sent by the portable device, performing facial feature comparison, and obtaining a facial comparison result includes: Acquire the facial features of the first user sent by the portable device; Based on the facial features of the first user and the facial features in a preset database, a facial feature comparison is performed to obtain the facial comparison result; wherein, if the facial feature comparison is successful, the facial comparison result includes the first information of the first user.

3. The method according to claim 1, characterized in that The semantic analysis result includes second information in the conversation voice data, where the second information represents the name of the target user; and obtaining the first information of the target user includes: Based on the second information, the first information of the target user is obtained by searching in a preset database.

4. The method according to claim 3, characterized in that The method further comprises: If the first information of the target user is not obtained, generating an introduction dialogue for the second information in the conversation voice data by the large language model according to a preset first prompt word and the conversation voice data; wherein the first prompt word is used to enable the large language model to determine the introduction dialogue; extracting the introduction dialogue according to the information category corresponding to the first information in the database to generate introduction information; Based on the introduction information and the acquired facial features of the first time period corresponding to the introduction dialogue, new first information is generated, so as to update the database based on the new first information.

5. The method according to claim 3, characterized in that: The searching in a preset database to obtain the first information of the target user includes: If the first information of multiple second users is retrieved from the database, the second user corresponding to the first information having the highest correlation with the conversation voice data is determined by the large language model according to a preset second prompt word and the conversation voice data; wherein the second prompt word is used to enable the large language model to determine the second user corresponding to the first information having the highest correlation with the conversation voice data; Based on the second user corresponding to the first information having the highest correlation with the conversation voice data, the first information of the target user is obtained by sorting the first information of a plurality of the second users.

6. The method according to claim 1, characterized in that The semantic analysis of the conversation speech data is performed by using the pre-trained large language model to obtain a semantic analysis result, including: A preset third prompt word and the conversation voice data are input into the large language model, and the large language model outputs the semantic analysis result; wherein the third prompt word is used to enable the large language model to determine whether second information exists in the conversation voice data, and if the second information exists, output the second information and related information that needs to be displayed for the target user; the second information represents the name of the target user.

7. An information display system, characterized in that: The system includes a portable device, a cloud server and a display device; The portable device is used to obtain facial features of the first user and send the facial features to the cloud server; and obtain conversation voice data related to the first user in the current environment and send the conversation voice data to the cloud server; The cloud server is used to: receiving the facial features sent by the portable device, performing facial feature comparison to obtain a facial comparison result, and sending the first information of the first user to the display device according to the facial comparison result; Receiving the pre-trained large language model sent by the portable device, performing semantic analysis on the conversation speech data, and obtaining a semantic analysis result; In a case where it is determined based on the semantic analysis result that relevant information of the target user needs to be displayed, first information of the target user is acquired, and user information to be displayed of the target user is generated by the large language model according to the semantic analysis result and the first information of the target user; Sending the user information to be displayed to a display device; The display device is used to display the first information of the first user and the to-be-displayed user information of the target user.

8. The system according to claim 7, characterized in that The portable device is specifically used for: Collecting facial images through a preset video acquisition module; The facial features are obtained by extracting features from the facial image using a preset feature extraction module.

9. An electronic device, characterized in that: include: processor; as well as A memory arranged to store computer executable instructions, wherein the executable instructions are configured to be executed by the processor, and the executable instructions include instructions for executing the information display method according to any one of claims 1 to 6.

10. A storage medium, characterized in that: The storage medium is used to store computer-executable instructions, and the computer-executable instructions enable a computer to execute the information display method according to any one of claims 1 to 6.

Images