Voice call management method, device, equipment, storage medium and product

Abstract

The present application discloses a voice call management method, device, equipment, storage medium and product, which relates to the field of voice call management technology, and discloses a voice call management method, including: when monitoring multi-user calls, collecting call content; extracting semantic features of the call content based on a preset semantic analysis model, analyzing the importance of each call content according to the extracted semantic features, the preset semantic analysis model is a model obtained by training the training model after semantically weighting the dialogue content of different discussion issues in each construction environment; adjusting the call volume of each user based on the importance. That is, when analyzing the importance of each call content, combined with the weight of each semantic, the output importance is made more in line with the current construction environment, so as to ensure accurate adjustment of the call volume of each user, so that the user can hear the key points of the call.

Description

Technical Field

[0001] The present application relates to the field of voice call management technology, and in particular to voice call management methods, devices, equipment, storage media and products. Background Art

[0002] As the application of voice intelligence becomes more and more extensive, voice intelligence has been widely used in safety helmets, so that users do not need to free up one hand to use a walkie-talkie to communicate when working with both hands, thus ensuring the safety of users.

[0003] Currently, the voice intelligence system on the helmet can open or close the conversation through voice control, completely freeing the hands. However, when the user is working, there may be multiple people talking at the same time, resulting in the user being unable to capture the key points of the conversation in time.

[0004] The above contents are only used to assist in understanding the technical solution of the present application and do not constitute an admission that the above contents are prior art. Summary of the invention

[0005] The main purpose of this application is to provide a voice call management method, which aims to solve the technical problem that users cannot hear the key points of the call in time from the conversation.

[0006] To achieve the above objectives, the present application proposes a voice call management method, the method comprising: When monitoring multi-user calls, collect the call content; Extracting semantic features of the call content based on a preset semantic analysis model, and analyzing the importance of each call content according to the extracted semantic features, wherein the preset semantic analysis model is a model obtained by training a to-be-trained model after semantically weighting the conversation content of different discussion issues in each construction environment; The call volume of each of the users is adjusted based on the importance level.

[0007] In one embodiment, when a multi-user call is detected, before the step of collecting the call content, the step further includes: Collect historical call content when emergencies occur in the current construction environment; Performing semantic analysis on the historical call content to determine a discussion question set when each emergency event occurs, and the discussion content of each discussion question in the discussion question set; Performing validity analysis on the discussion contents to determine the effective weight of each discussion content for the corresponding discussion issue; The preset model to be trained is trained based on the effective weights, the discussion questions and the discussion content to obtain a preset semantic model.

[0008] In one embodiment, the step of performing validity analysis on the discussion content to determine the effective weight of each discussion content for the corresponding discussion question includes: Simulate the process of solving the corresponding discussion problem according to the discussion content, and determine the contribution of each discussion content in solving the discussion problem; The effective weight of each discussion content for the corresponding discussion question is determined based on the contribution degree.

[0009] In one embodiment, the step of performing semantic analysis on the historical call content to determine a discussion question set when each emergency event occurs and the discussion content of each discussion question in the discussion question set includes: Performing semantic analysis on the historical call contents to determine the central topic in each of the historical call contents and related topics extending from the central topic; Determining the degree of relevance between the related topics and the central topic based on the semantics of the historical call content; Based on the degree of association, the central topic and the related topics are screened to obtain effective topics when each emergency occurs; Extracting corresponding discussion questions and corresponding discussion contents from the effective topics; Priorities are assigned to the discussion questions according to the relevance of each of the valid topics to obtain a discussion question set.

[0010] In one embodiment, the step of adjusting the call volume of each user based on the importance level includes: Based on the importance level, preliminarily determine the provisional call volume of each user, and obtain the source ID of each call content; Determine whether there is a signal source marked as a command in the source ID; If there is a signal source marked as a command, the call volume of the user corresponding to the signal source marked as a command is determined as the highest volume of all the users; The call volume of the corresponding user is adjusted based on the maximum volume.

[0011] In one embodiment, if there is a signal source marked as a command, the step of determining the call volume of the user corresponding to the signal source marked as a command as the highest volume of each of the users includes: If there is a signal source marked as a command, identifying the target call content of the user corresponding to the signal source marked as a command; Determine the purpose of the current call based on the call content of each user; Identifying the relevance of the target call content to the call purpose; If the correlation degree is greater than a preset value, the call volume of the user corresponding to the signal source marked as command is determined as the highest volume of each of the users.

[0012] In addition, to achieve the above purpose, the present application also proposes a voice call management device, the voice call management device comprising: The collection module is used to collect the content of calls when monitoring multiple users' calls; An analysis module, used to extract semantic features of the call content based on a preset semantic analysis model, and analyze the importance of each call content according to the extracted semantic features, wherein the preset semantic analysis model is a model obtained by training a to-be-trained model after semantically weighting each conversation content of different discussion issues in the current construction environment; The adjustment module is used to adjust the call volume of each user based on the importance.

[0013] In addition, to achieve the above objectives, the present application also proposes a voice call management device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the voice call management method described above.

[0014] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by the processor, the steps of the voice call management method described above are implemented.

[0015] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, the steps of the voice call management method described above are implemented.

[0016] One or more technical solutions proposed in this application have at least the following technical effects: When a multi-user call is detected, the call content of each user participating in the call is collected, and the preset semantic analysis model is used to extract semantic features of the call content. The importance of each user's call content is analyzed based on the extracted semantic features. Finally, the call volume of each user is adjusted according to the importance to highlight the key content of this call. The preset semantic analysis model is obtained by training the training model after semantically weighting the dialogue content of different discussion issues in each construction environment. When analyzing the importance of each call content, the weight of each semantic can be combined to make the output importance more in line with the current construction environment, so as to ensure accurate adjustment of the call volume of each user and avoid shielding important call content, thereby enabling users to hear the key content of the call. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0018] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0019] Figure 1 A flowchart of the first embodiment of the voice call management method of the present application is provided; Figure 2 A flowchart of the second embodiment of the voice call management method of the present application is provided; Figure 3 A flowchart of the third embodiment of the voice call management method of the present application is provided; Figure 4 This is a schematic diagram of the module structure of the voice call management device according to an embodiment of the present application; Figure 5 This is a schematic diagram of the device structure of the hardware operating environment involved in the voice call management method in the embodiment of the present application.

[0020] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0021] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0022] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0023] The main solution of the embodiment of the present application is: when the voice controller detects a multi-user conversation, it collects the call content; based on a preset semantic analysis model, semantic features of the call content are extracted, and the importance of each call content is analyzed according to the extracted semantic features. The preset semantic analysis model is a model obtained by training the training model after semantically weighting the dialogue content of different discussion issues in each construction environment; based on the importance, the call volume of each user is adjusted.

[0024] In this embodiment, for ease of description, the following description is made with the voice controller as the execution subject.

[0025] At present, the voice intelligent system on the helmet can open or close the conversation through voice control, completely freeing the hands. However, when the user is working, there may be multiple people talking at the same time, resulting in the user being unable to capture the key points from the conversation in time.

[0026] The present application provides a solution. When a multi-user call is detected, the call content of each user participating in the call is collected, and the semantic features of the call content are extracted using a preset semantic analysis model. The importance of the call content of each user is analyzed based on the extracted semantic features. Finally, the call volume of each user is adjusted based on the importance to highlight the key content of this call. The preset semantic analysis model is obtained by training the training model after semantically weighting the dialogue content of different discussion issues in each construction environment. When analyzing the importance of each call content, the weight of each semantic can be combined to make the output importance more in line with the current construction environment, so as to ensure accurate adjustment of the call volume of each user and avoid shielding important call content, thereby enabling users to hear the key content of the call.

[0027] It should be noted that the execution subject of this embodiment can be a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or an electronic device capable of realizing the above functions, a voice controller, etc. The following takes the voice controller as an example to illustrate this embodiment and the following embodiments.

[0028] Based on this, the present application embodiment provides a voice call management method, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the voice call management method of the present application.

[0029] In this embodiment, the voice call management method includes steps S10 to S30: Step S10, when a multi-user call is detected, the call content is collected; It should be noted that the users are construction users who work with safety helmets and construction command users. A multi-user call is a multi-user call between multiple construction users or command users at the same time. The call content is the content of the communication between multiple construction users and / or command users during the multi-user call. The call content can be, but is not limited to, a discussion on a certain construction problem, and can also be content about the promotion of safe construction, etc.

[0030] In a specific implementation, when the voice call module of the helmet is monitored to receive voice signals from multiple users wearing helmets, it is determined that a multi-user call is currently ongoing. During the multi-user call, the call content of each user is collected in real time to facilitate the subsequent determination of the call volume of each user based on the call content.

[0031] Step S20, extracting semantic features of the call content based on a preset semantic analysis model, and analyzing the importance of each call content according to the extracted semantic features, wherein the preset semantic analysis model is a model obtained by training a to-be-trained model after semantically weighting the conversation content of different discussion issues in each construction environment; It should be noted that the preset semantic analysis model is a pre-built neural network model used to analyze and understand the semantic information in text or voice data. Semantic features may include but are not limited to keywords, phrases, and syntactic structures, which together constitute the semantic representation of text or voice. The degree of importance refers to the degree of association with the topic of the call. For example, if the topic of the call content revolves around security, the more valid security-related topics in the call content of each user, the higher its importance. Semantic weighting is to weight each semantic feature according to the degree of association between semantics and topics, so as to determine the importance of each user's call content after weighting the extracted semantic features.

[0032] It is understandable that there may be a large amount of noise at the construction site. During a call between multiple users, the noise will be transmitted to the voice call module of the other users' helmets along with the call signal, or multiple people may speak at the same time during the call. Therefore, after obtaining the call content, it is necessary to first use the preset semantic analysis model to denoise the call content, and then analyze the semantic features of each call content after denoising to avoid noise interference in the analysis of the call content, thereby improving the accuracy of the preset semantic analysis model in extracting semantic features of the call content.

[0033] It can be understood that since the preset semantic analysis model is a model obtained by training the training model after semantically weighting the conversation content of different discussion issues in each construction environment, the preset semantic analysis model is used to identify the semantic features of the call content, thereby ensuring that the extracted semantic features can adapt to the current scene more accurately. For example, if the current scene is mine construction, then when weighting the semantic features, topics related to mine construction can be given a higher weight to avoid call content irrelevant to the current scene affecting the final importance analysis, thereby improving the semantic analysis model's analysis of the importance of call content.

[0034] Step S30: adjusting the call volume of each user based on the importance level.

[0035] It should be noted that the call volume can be the call volume of other users played by the user when the user talks with other users through the helmet, that is, the higher the importance, the higher the call volume played, and the lower the importance, the lower the call volume played.

[0036] It can be understood that after determining the importance of each user's call content, the call volume of more important users is increased and the call volume of less important users is decreased, so as to highlight the important call content in the call, prevent users from missing important call content, and enable users to hear the key points of the call.

[0037] It should be noted that the adjustment of the user's call volume is real-time, and the volume is gradually reduced or increased to avoid sudden increase or decrease in volume that affects the user's attention in communication.

[0038] It is understandable that by dynamically adjusting the user's call volume, important speeches during the call can be made clearer and minor speeches can be relatively weakened, thereby enhancing the user's call experience. In scenarios where professional discussions are required, such as problem discussions in construction environments, the quality and efficiency of communication can be significantly improved.

[0039] This embodiment provides a voice call management method. When a multi-user call is detected, the call content of each user participating in the call is collected, and the preset semantic analysis model is used to extract semantic features of the call content, and the importance of each user's call content is analyzed based on the extracted semantic features. Finally, according to the importance, the call volume of each user is adjusted to highlight the key content of this call. The preset semantic analysis model is obtained by training the training model after semantically weighting the dialogue content of different discussion issues in each construction environment. When analyzing the importance of each call content, the weight of each semantic can be combined to make the output importance more in line with the current construction environment, so as to ensure accurate adjustment of the call volume of each user and avoid shielding important call content, thereby achieving the goal of allowing users to hear the key content of the call.

[0040] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the above-mentioned embodiment 1 can refer to the above introduction, and will not be repeated later. Figure 2 Before step S10, the voice call management method further includes steps S01 to S04: Step S01, collecting historical call contents when an emergency occurs in the current construction environment; Step S02, performing semantic analysis on the historical call content to determine a discussion question set when each emergency event occurs, and the discussion content of each discussion question in the discussion question set; Step S03, performing validity analysis on the discussion content to determine the effective weight of each discussion content for the corresponding discussion question; Step S04: training a preset model to be trained based on the effective weights, the discussion questions and the discussion content to obtain a preset semantic model.

[0041] It should be noted that the current construction environment is a place where construction activities are ongoing, including but not limited to construction sites, infrastructure construction sites, mines, and power operation sites. An emergency is an event that occurs suddenly during the construction process and may affect the construction progress, personnel safety, equipment status, etc., and requires communication. The historical call content is the call records between construction personnel in the past construction process, especially when an emergency occurs. These records can be in the form of voice recordings, text transcriptions, etc., and are not specifically limited. Semantic analysis is to analyze text or voice data through natural language processing technology to extract semantic information, for example, to identify keywords, topics, emotional tendencies, etc. in the call. The discussion problem set is the set of main issues discussed by each construction personnel when an emergency occurs, and each discussion problem set includes at least one specific discussion problem. The discussion content is the specific opinions, suggestions, decisions, etc. expressed by the construction personnel in the call for each discussion problem. The effectiveness analysis is to evaluate the actual role and contribution of each discussion content in solving the corresponding discussion problem, for example, whether a certain discussion content provides key information and whether it helps solve the problem. The effective weight is a value assigned to each discussion content based on the results of the effectiveness analysis, indicating its importance in solving the corresponding discussion problem. The higher the weight, the more important the discussion content is.

[0042] It is understandable that by conducting semantic analysis and effectiveness evaluation on historical call content, a preset semantic model is trained that can automatically identify and analyze call content, thereby helping construction personnel to hear important call content more accurately during calls, avoiding delays in work caused by construction personnel's inability to respond to call content in a timely manner, and thus improving the emergency response capabilities of the construction environment.

[0043] In the specific implementation, historical call contents when emergencies occur in the current construction environment are collected. These contents will serve as the basic data for analysis and training models, and semantic analysis will be performed on historical call contents to determine the discussion question sets when each emergency occurs, as well as the discussion contents of each discussion question in the discussion question set. The effectiveness of the discussion contents will be analyzed to determine the effective weight of each discussion content for the corresponding discussion question. Through machine learning algorithms, combined with effective weights and discussion contents, a model that can recognize and process similar call contents will be trained.

[0044] Furthermore, step S03 also includes: Simulate the process of solving the corresponding discussion problem according to the discussion content, and determine the contribution of each discussion content in solving the discussion problem; The effective weight of each discussion content for the corresponding discussion question is determined based on the contribution degree.

[0045] It should be noted that contribution refers to the role or influence of a discussion content in solving the discussion problem. The level of contribution reflects the value and importance of the discussion content. For example, if a discussion content proposes an effective solution, its contribution will be higher.

[0046] It can be understood that by simulating the process of solving corresponding problems based on the discussion content, the actual effect of the discussion content on the problem to be solved can be determined. Since the simulation process can comprehensively consider historical situations to determine the process of problem solving, the contribution of the determined discussion content in solving the discussion problem can be closer to the actual situation, thereby improving the accuracy of the effective weights of each discussion content for the corresponding discussion problem.

[0047] Furthermore, step S02 further includes: Performing semantic analysis on the historical call contents to determine the central topic in each of the historical call contents and related topics extending from the central topic; Determining the degree of relevance between the related topics and the central topic based on the semantics of the historical call content; Based on the degree of association, the central topic and the related topics are screened to obtain effective topics when each emergency occurs; Extracting corresponding discussion questions and corresponding discussion contents from the effective topics; Priorities are assigned to the discussion questions according to the relevance of each of the valid topics to obtain a discussion question set.

[0048] It should be noted that the central topic refers to the core topic that occupies a dominant position and is frequently mentioned in a historical call content. It is usually the main issue of concern to both parties or the core content of the discussion. For example, in a call about construction safety, "safety net" may be the central topic. Related topics refer to secondary topics that have a certain relevance or extension to the central topic, which are usually naturally introduced in the process of discussing the central topic. For example, when "safety net" is the central topic, "construction of safety net" and "quality of safety net" can be related topics. The degree of relevance refers to the correlation or closeness between the related topics and the central topic. It can be determined by semantic analysis technology, for example, calculating the frequency of co-occurrence of related topics and central topics in the text, semantic similarity, etc. The higher the degree of relevance, the closer the relationship between the related topics and the central topic. Priority assignment refers to the process of prioritizing the discussion issues according to their importance and urgency.

[0049] It can be understood that through semantic analysis technology, the deep semantic information in the content of historical calls can be accurately captured, and then the effective topics can be refined and organized based on the semantic information, so as to better utilize the valuable information in the content of historical calls, enhance the availability of information, and improve the accuracy of information extraction. Finally, by screening and assigning priorities to central topics and related topics, key information can be quickly located and the efficiency of information processing can be improved.

[0050] In the specific implementation, through the semantic analysis of the content of historical calls, the discussion issues and their related contents that may arise in various emergencies are determined, and the semantics of each call content is obtained. The semantics are then analyzed to determine the degree of correlation between each related topic and the corresponding central topic, so as to facilitate the screening of valid topics that are highly relevant to the central topic based on the degree of correlation. After determining the valid topics, specific discussion issues and discussion contents are extracted from the valid topics, and each discussion issue is assigned a priority based on the degree of correlation to form a discussion issue set.

[0051] Based on the first and second embodiments of the present application, in the third embodiment of the present application, the same or similar contents as those in the above embodiments can be referred to the above introduction, and will not be described in detail later. Figure 3 , step S30 also includes steps S1 to S4: Step S1, preliminarily determining the provisional call volume of each user based on the importance level, and obtaining the source ID of each call content; Step S2, determining whether there is a signal source marked as a command in the source ID; Step S3, if there is a signal source marked as a command, the call volume of the user corresponding to the signal source marked as a command is determined as the highest volume of each of the users; Step S4: adjusting the call volume of the corresponding user based on the maximum volume.

[0052] It should be noted that the provisional call volume is a preliminary setting of the call volume based on the importance of the user, that is, the provisional call volume is not the final volume setting, but serves as the basis for subsequent adjustments. The source ID is a unique identifier that identifies the source of the call content. Each user participating in the call has a unique source ID, which is used to distinguish different call content. For example, in a multi-person video conference, the source ID of each participant can help the system identify who is speaking. The command signal source is the signal sent by the user who has a command or leadership role in the call. Usually, the command signal source corresponds to the leader or coordinator in the call. The maximum volume is the highest volume setting among all call volumes. The maximum volume is usually used to emphasize the most important or urgent call content.

[0053] It can be understood that by adjusting the volume based on the importance and source of the command signal, it is ensured that important information and command instructions can be clearly conveyed to avoid omissions or misunderstandings of information due to volume issues.

[0054] It is understandable that since the command signal source comes from the designer or supervisor, when the command signal source is detected, it is necessary to give priority to allowing the user to hear the designer's or supervisor's conversation content to avoid the designer's or supervisor's wishes not being implemented by the construction workers.

[0055] In a specific implementation, when an emergency is discussed using the voice call module of a safety helmet during a construction process, the project manager or chief designer is of the highest importance, and his or her call content is marked as a command signal source. Therefore, it is necessary to first preliminarily determine the provisional call volume of each user based on the importance, and then detect that the call content of the project manager or chief designer is a command signal source, set his or her call volume to the highest volume, and adjust the call volumes of other users accordingly based on the highest volume to ensure that the project manager's instructions can be clearly conveyed.

[0056] Furthermore, step S3 further includes: If there is a signal source marked as a command, identifying the target call content of the user corresponding to the signal source marked as a command; Determine the purpose of the current call based on the call content of each user; Identifying the relevance of the target call content to the call purpose; If the correlation degree is greater than a preset value, the call volume of the user corresponding to the signal source marked as command is determined as the highest volume of each of the users.

[0057] It should be noted that the target call content refers to the specific content said by the user corresponding to the signal source marked as a command during the call. The call purpose is the core intention or main task of the entire call, that is, the goal that all participants hope to achieve through the call, including but not limited to solving problems, conveying important information, coordinating actions, etc. The relevance is the degree of correlation between the target call content and the current call purpose. The semantic features of the call content can be analyzed to evaluate its match with the call purpose. Default value: This is a pre-set threshold used to determine whether the relevance of the target call content to the call purpose is high enough.

[0058] It is understandable that since the user of the command signal source may say something that has nothing to do with, or is of little relevance to the call target, in order to prevent the user from missing important information of other users due to such content, when it is detected that the target call content of the user corresponding to the signal source marked as command has a correlation with the call purpose that is greater than a preset value, the target call content is determined to be valid call content, thereby improving the flexibility of voice management and avoiding treating any command user's information as important content.

[0059] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the voice call management method of the present application. More simple transformations based on this technical concept are all within the scope of protection of the present application.

[0060] This application also provides a voice call management device, please refer to Figure 4 , the voice call management device comprises: The collection module 10 is used to collect the content of the calls when multiple users are talking; An analysis module 20 is used to extract semantic features of the call content based on a preset semantic analysis model, and analyze the importance of each call content according to the extracted semantic features. The preset semantic analysis model is a model obtained by training a to-be-trained model after semantically weighting each conversation content of different discussion issues in the current construction environment; The adjustment module 30 is configured to adjust the call volume of each user based on the importance level.

[0061] Optionally, the analysis module 20 is also used to collect historical call contents when emergencies occur in the current construction environment; perform semantic analysis on the historical call contents to determine a set of discussion questions when each emergency occurs, and the discussion content of each discussion question in the discussion question set; perform validity analysis on the discussion contents to determine the effective weight of each discussion content for the corresponding discussion question; train a preset model to be trained based on the effective weight, the discussion question and the discussion content to obtain a preset semantic model.

[0062] Optionally, the analysis module 20 is further used to simulate the process of solving the corresponding discussion problem based on the discussion content, determine the contribution of each discussion content in solving the discussion problem; and determine the effective weight of each discussion content for the corresponding discussion problem based on the contribution.

[0063] Optionally, the analysis module 20 is also used to perform semantic analysis on the historical call content to determine the central topic in each of the historical call contents, as well as related topics extending from the central topic; based on the semantics of the historical call content, determine the degree of correlation between the related topics and the central topic; based on the degree of correlation, screen the central topic and the related topics to obtain effective topics when various emergencies occur; extract corresponding discussion questions and corresponding discussion contents from the effective topics; assign priorities to the discussion questions according to the degree of correlation between the effective topics to obtain a set of discussion questions.

[0064] Optionally, the adjustment module 30 is also used to preliminarily determine the tentative call volume of each of the users based on the level of importance, and obtain the source ID of each of the call contents; determine whether there is a signal source marked as command in the source ID; if there is a signal source marked as command, determine the call volume of the user corresponding to the signal source marked as command as the highest volume of each of the users; and adjust the call volume of the corresponding user based on the highest volume.

[0065] Optionally, the adjustment module 30 is also used to identify the target call content of the user corresponding to the signal source marked as command if there is a signal source marked as command; determine the call purpose of the current call based on the call content of each user; identify the correlation between the target call content and the call purpose; if the correlation is greater than a preset value, determine the call volume of the user corresponding to the signal source marked as command as the highest volume of each of the users.

[0066] The voice call management device provided by the present application adopts the voice call management method in the above embodiment, which can solve the technical problem that the user cannot hear the key points of the call in time from the conversation. Compared with the prior art, the beneficial effects of the voice call management device provided by the present application are the same as the beneficial effects of the voice call management method provided by the above embodiment, and the other technical features in the voice call management device are the same as the features disclosed in the above embodiment method, which will not be repeated here.

[0067] The present application provides a voice call management device, which includes: at least one processor; and a memory that is communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the voice call management method in the above-mentioned embodiment one.

[0068] Reference below Figure 5, which shows a schematic diagram of the structure of a voice call management device suitable for implementing the embodiment of the present application. The voice call management device in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 5 The voice call management device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0069] like Figure 5 As shown, the voice call management device may include a processing device 1001 (e.g., a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM: Random Access Memory) 1004. In RAM1004, various programs and data required for the operation of the voice call management device are also stored. The processing device 1001, ROM1002, and RAM1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems can be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD: Liquid Crystal Display), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the voice call management device to communicate with other devices wirelessly or by wire to exchange data. Although the figure shows a voice call management device with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems can be implemented or have alternatively.

[0070] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0071] The voice call management device provided by the present application adopts the voice call management method in the above embodiment, which can solve the technical problem that the user cannot hear the key points of the call in time from the conversation. Compared with the prior art, the beneficial effects of the voice call management device provided by the present application are the same as the beneficial effects of the voice call management method provided by the above embodiment, and the other technical features in the voice call management device are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0072] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0073] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0074] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, and the computer-readable program instructions are used to execute the voice call management method in the above-mentioned embodiment.

[0075] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM: Random Access Memory), a read-only memory (ROM: Read Only Memory), an erasable programmable read-only memory (EPROM: Erasable Programmable Read Only Memory or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM: CD-Read Only Memory), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency: Radio Frequency), etc., or any suitable combination of the above.

[0076] The computer-readable storage medium may be included in the voice call management device; or may exist independently without being assembled into the voice call management device.

[0077] The above-mentioned computer-readable storage medium carries one or more programs. When the above-mentioned one or more programs are executed by the voice call management device, the voice call management device: collects call content when monitoring multi-user calls; extracts semantic features of the call content based on a preset semantic analysis model, and analyzes the importance of each call content according to the extracted semantic features, wherein the preset semantic analysis model is a model obtained by training the training model after semantically weighting the dialogue content of different discussion issues in each construction environment; and adjusts the call volume of each user based on the importance.

[0078] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0079] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0080] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.

[0081] The readable storage medium provided by the present application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned voice call management method, and can solve the technical problem that the user cannot hear the key points of the call from the conversation in time. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided by the present application are the same as the beneficial effects of the voice call management method provided by the above-mentioned embodiment, and will not be repeated here.

[0082] The present application also provides a computer program product, including a computer program, which implements the steps of the above-mentioned voice call management method when executed by a processor.

[0083] The computer program product provided by the present application can solve the technical problem that the user cannot hear the key points of the call in time from the conversation. Compared with the prior art, the beneficial effects of the computer program product provided by the present application are the same as the beneficial effects of the voice call management method provided by the above embodiment, which will not be repeated here.

[0084] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A voice call management method, characterized in that: The method includes: When monitoring multi-user calls, collect the call content; Extracting semantic features of the call content based on a preset semantic analysis model, and analyzing the importance of each call content according to the extracted semantic features, wherein the preset semantic analysis model is a model obtained by training a to-be-trained model after semantically weighting the conversation content of different discussion issues in each construction environment; The call volume of each of the users is adjusted based on the importance level.

2. The method according to claim 1, characterized in that When a multi-user call is detected, the step of collecting the call content also includes: Collect historical call content when emergencies occur in the current construction environment; Performing semantic analysis on the historical call content to determine a discussion question set when each emergency event occurs, and the discussion content of each discussion question in the discussion question set; Performing validity analysis on the discussion contents to determine the effective weight of each discussion content for the corresponding discussion issue; The preset model to be trained is trained based on the effective weights, the discussion questions and the discussion content to obtain a preset semantic model.

3. The method according to claim 2, characterized in that The step of analyzing the effectiveness of the discussion content to determine the effective weight of each discussion content for the corresponding discussion question includes: Simulate the process of solving the corresponding discussion problem according to the discussion content, and determine the contribution of each discussion content in solving the discussion problem; The effective weight of each discussion content for the corresponding discussion question is determined based on the contribution degree.

4. The method according to claim 2, characterized in that The step of performing semantic analysis on the historical call content to determine a discussion question set when each emergency event occurs and the discussion content of each discussion question in the discussion question set includes: Performing semantic analysis on the historical call contents to determine the central topic in each of the historical call contents and related topics extending from the central topic; Determining the degree of relevance between the related topics and the central topic based on the semantics of the historical call content; Based on the degree of association, the central topic and the related topics are screened to obtain effective topics when each emergency occurs; Extracting corresponding discussion questions and corresponding discussion contents from the effective topics; Priorities are assigned to the discussion questions according to the relevance of each of the valid topics to obtain a discussion question set.

5. The method according to claim 1, characterized in that The step of adjusting the call volume of each user based on the importance level comprises: Based on the importance level, preliminarily determine the provisional call volume of each user, and obtain the source ID of each call content; Determine whether there is a signal source marked as a command in the source ID; If there is a signal source marked as a command, the call volume of the user corresponding to the signal source marked as a command is determined as the highest volume of all the users; The call volume of the corresponding user is adjusted based on the maximum volume.

6. The method according to claim 5, characterized in that If there is a signal source marked as a command, the step of determining the call volume of the user corresponding to the signal source marked as a command as the highest volume of each user comprises: If there is a signal source marked as a command, identifying the target call content of the user corresponding to the signal source marked as a command; Determine the purpose of the current call based on the call content of each user; Identifying the relevance of the target call content to the call purpose; If the correlation degree is greater than a preset value, the call volume of the user corresponding to the signal source marked as command is determined as the highest volume of each of the users.

7. A voice call management device, characterized in that: The device comprises: The collection module is used to collect the content of calls when monitoring multiple users' calls; An analysis module, used to extract semantic features of the call content based on a preset semantic analysis model, and analyze the importance of each call content according to the extracted semantic features, wherein the preset semantic analysis model is a model obtained by training a to-be-trained model after semantically weighting each conversation content of different discussion issues in the current construction environment; The adjustment module is used to adjust the call volume of each user based on the importance.

8. A voice call management device, characterized in that: The device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the voice call management method according to any one of claims 1 to 6.

9. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the voice call management method according to any one of claims 1 to 6 are implemented.

10. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the steps of the voice call management method according to any one of claims 1 to 6 are implemented.

Images