A method and system for evaluating the quality of tour guide explanations

Abstract

A method and system for evaluating the quality of tour guide presentations are disclosed. This method involves configuring a presentation outline for each project, including pre-defined key points; establishing presentation quality control rules to assess the presentation quality of key points, including accuracy, pace, and emotional delivery; training an NLP quality control model based on the intentions and quality control rules outlined in the presentation outline; acquiring real-time recordings of the tour guide's presentations and converting them into transcripts; feeding the transcripts into the NLP quality control model for analysis; and using the NLP model to evaluate the quality of the real-time recordings. This invention enables the recording and evaluation of tour guide performance, preventing omissions of key content, ensuring the effectiveness of presentations, and guaranteeing overall presentation quality.

Description

Technical Field

[0001] This invention belongs to the field of data processing technology, specifically relating to a method and system for evaluating the quality of a presenter's explanations. Background Technology

[0002] Currently, tour guides play a vital role in various industries, from tour guides in tourism to exhibition hall presenters in companies, and project presenters in large-scale projects. When delivering a presentation, tour guides must ensure the completeness of the content to guarantee that the audience fully understands the information. If a tour guide omits or makes a mistake, the audience will receive incorrect information, make incorrect judgments, and ultimately, the project may fail.

[0003] Currently, there are no relevant recording and monitoring systems for tour guides' performance. When tour guides deviate from the planned content, there are no corresponding countermeasures, no way to assess them, and no data-driven quantification measures. Under these circumstances, key content may be missed, and the effectiveness of the tour cannot be guaranteed. Summary of the Invention

[0004] To address this issue, the present invention provides a method and system for evaluating the quality of a tour guide's explanations, thereby solving the problem that existing technologies lack assessment and evaluation of tour guides' explanations, which fails to guarantee the effectiveness of the explanations.

[0005] To achieve the above objectives, the present invention provides the following technical solution: a method for evaluating the quality of a tour guide's presentation, comprising:

[0006] Configure an outline for the project to be explained, which includes the key points of the project to be explained.

[0007] Establish quality inspection rules for explanations, and judge the explanation of key points based on the explanation quality inspection rules. The explanation of key points includes whether the explanation of key points is correct and in place, the speed of the explanation, and whether the explanation of emotions is appropriate and in place.

[0008] The intentions and quality inspection rules mentioned in the outline are used to train an NLP quality inspection model.

[0009] Acquire real-time audio recordings of tour guides and convert them into written explanations.

[0010] The text of the explanation is fed into an NLP quality control model for understanding, and the NLP quality control model is used to perform quality control and judgment on the real-time audio recording of the explanation.

[0011] As a preferred method for evaluating the quality of a lecturer's presentation, in the process of judging whether the presentation is adequate, each knowledge point in the key points of the presentation is made into an intent using an NLP engine. If the presentation hits the specified intent, it is determined that the corresponding knowledge point has been presented.

[0012] The number of hits determines whether the key points of the explanation have been explained effectively.

[0013] As a preferred method for evaluating the quality of tour guide explanations, the process of judging the speaking speed adopts oral assessment technology. When the voice passes through the oral assessment engine, the oral assessment engine is used to judge the speaking speed.

[0014] The speaking speed is compared with the preset speaking speed. When the speaking speed exceeds the preset speaking speed threshold, the speaking speed is judged to be abnormal.

[0015] As a preferred method for evaluating the quality of a tour guide's explanation, the process of judging whether the emotional tone of the explanation is correct and appropriate involves determining whether the tone of the explanation matches the preset emotional type based on preset voice parameters.

[0016] Sound parameters include volume and amplitude; preset emotion types include anger, happiness, and calmness.

[0017] As a preferred method for evaluating the quality of tour guide explanations, it records and pushes key points that tour guides miss, or provides real-time reminders to tour guides that they lack pre-set key points in designated segments.

[0018] This invention also provides a system for evaluating the quality of tour guide presentations, comprising:

[0019] The explanation outline configuration module is used to configure the explanation outline for the explanation project. The explanation outline includes the key points of the explanation project that are preset.

[0020] The quality inspection rule configuration module is used to formulate the explanation quality inspection rules and judge the explanation of key points based on the explanation quality inspection rules. The explanation of key points includes whether the explanation of key points is correct and in place, the speed of the explanation, and whether the explanation of emotion is appropriate and in place.

[0021] The quality inspection model training module is used to train the intentions and quality inspection rules involved in the explanation outline to form an NLP quality inspection model.

[0022] The audio recording module is used to acquire real-time audio recordings of the narrator and convert them into audio text.

[0023] The quality control module is used to feed the narration text into the NLP quality control model for understanding, and to perform quality control on the narrator's real-time narration recording through the NLP quality control model.

[0024] As an interpreter explaining the optimal solution of the quality evaluation system, in the quality inspection rule configuration module, each knowledge point in the key points of the explanation is made into an intent using an NLP engine. If the explanation hits the specified intent, it is determined that the corresponding knowledge point has been explained. The number of intents hit is used to determine whether the specified key points of the explanation have been explained in place.

[0025] As the preferred solution for the quality evaluation system for tour guides, the quality inspection rule configuration module uses oral assessment technology. When the voice passes through the oral assessment engine, the oral assessment engine is used to determine the speaking speed. The speaking speed is compared with the preset speaking speed, and when it exceeds the preset speaking speed threshold, the speaking speed is judged to be abnormal.

[0026] As part of the optimal solution for the quality evaluation system for tour guides, the quality inspection rule configuration module determines whether the tour guide's voice matches a preset emotional type based on preset voice parameters. These parameters include volume and amplitude; the preset emotional types include anger, happiness, and calmness.

[0027] As a preferred solution for the tour guide quality evaluation system, it also includes a missed explanation module, which is used to record and push key points of the tour guide's explanation that are missed, or to remind the tour guide in real time that there are no preset key points of explanation in a specified segment.

[0028] This invention has the following advantages: It configures a narration outline for each narration project, including pre-defined key points; it establishes narration quality inspection rules to judge the narration of key points, including whether the key points are correctly and appropriately presented, the speaking speed, and the appropriateness of the emotional delivery; it trains the intentions and narration quality inspection rules within the narration outline to form an NLP quality inspection model; it acquires real-time narration recordings of the narrators and converts them into transcripts; it feeds the transcripts into the NLP quality inspection model for understanding and performs quality inspection on the narrators' real-time narration recordings. This invention enables the recording and evaluation of narrators' narration levels, avoids omitting key content, ensures the effectiveness of the narration, and guarantees the quality of the narration. Attached Figure Description

[0029] To more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are merely exemplary, and those skilled in the art can derive other embodiments based on the provided drawings without creative effort.

[0030] Figure 1 This is a schematic diagram of the process of an interpreter explaining the quality evaluation method provided in Embodiment 1 of the present invention;

[0031] Figure 2 This is a schematic diagram of the instructor's explanation quality evaluation system provided in Embodiment 2 of the present invention. Detailed Implementation

[0032] The following specific embodiments illustrate the implementation of the present invention. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0033] Because existing technologies lack recording and monitoring systems for tour guide performance, there are no effective countermeasures when guides deviate from the planned content, making it impossible to assess their abilities or quantify their performance. This can lead to omissions of key content and compromised presentation quality. Therefore, this invention provides the following specific technical solution to address the problem of insufficient assessment and evaluation of tour guide performance in existing technologies, which hinders the guarantee of effective presentations.

[0034] Example 1

[0035] See Figure 1 Embodiment 1 of the present invention provides a method for evaluating the quality of a tour guide's explanation, comprising:

[0036] S1. Configure the explanation outline for the explanation project, wherein the explanation outline includes the key points of the explanation project that are preset.

[0037] S2. Formulate explanation quality inspection rules, and judge the explanation of key points according to the explanation quality inspection rules. The explanation of key points includes whether the explanation of key points is correct and in place, the speed of the explanation, and whether the explanation of emotions is appropriate and in place.

[0038] S3. Train the intentions and quality inspection rules involved in the explanation outline to form an NLP quality inspection model;

[0039] S4. Obtain the real-time audio recording of the guide's explanation and convert the real-time audio recording into text explanation;

[0040] S5. The explanatory text is fed into the NLP quality inspection model for understanding, and the NLP quality inspection model is used to perform quality inspection and judgment on the real-time audio recording of the narrator's explanation.

[0041] The application scenario of this embodiment is as follows: it is applied to a wearable hardware device that combines edge and cloud computing, and a cloud-based data management system. The tour guide wears the hardware device, which can record the tour guide's audio and interact with data from the network and cloud. The cloud management system can be configured with a narration outline that includes key points of the narration, and analyzes the data uploaded by the device. Based on the narration, it determines whether the tour guide's narration is complete. If the narration is incomplete, a score is given, and if necessary, the wearable device can notify the tour guide to supplement the narration.

[0042] In this embodiment, the guide or manager configures and uploads key points for the presentation, i.e., the presentation outline, in the cloud. Different emphases can be configured for different project types. The guide or manager formulates presentation quality inspection rules. When the guide's presentation meets the quality inspection rules, it is determined that the presentation point has been completed. Depending on the presentation type and the audience, configurable content includes whether a certain point has been covered, whether the explanation of a certain point is sufficient and thorough, whether the presentation point is correct, the speaking speed, the tone of voice, and whether there is interaction, etc.

[0043] In this embodiment, during the process of determining whether the explanation is adequate, each knowledge point in the key points of the explanation is made into an intent using an NLP engine. If the explanation hits the specified intent, it is determined that the corresponding knowledge point has been explained. The number of hit intents is used to determine whether the specified key points of the explanation have been explained adequately.

[0044] Specifically, a key point in the explanation can be composed of multiple knowledge points. Each knowledge point is used to create an intent using an NLP engine. When the explanation hits the intent, it means that the knowledge point has been explained. The number of intents that are hit can be used to judge whether the explanation is sufficient.

[0045] Specifically, NLP engines are existing technology. They can translate human language into machine-readable form, allowing machines to extract meaning from provided data. The content of the explanation outline is pre-annotated and trained into an intent model using frameworks such as BERT. This trained intent model is then used as an NLP quality control model to perform quality checks on the presenter's script.

[0046] In this embodiment, the process of determining the speaking speed is explained using oral assessment technology. When the speech passes through the oral assessment engine, the oral assessment engine is used to determine the speaking speed. The speaking speed is compared with the preset speaking speed, and when it exceeds the preset speaking speed threshold, the speaking speed is determined to be abnormal.

[0047] Specifically, by utilizing relatively mature oral assessment technology, when speech passes through the oral assessment engine, the engine's ability can be used to determine the speech rate and compare it with the preset speech rate. When the speech rate exceeds the threshold, it can be determined that the speech rate is abnormal.

[0048] Spoken language assessment technology is based on computer technology, pattern recognition technology, and intelligent signal processing technology. It can automatically assess and diagnose spoken language pronunciation quality based on the physiological characteristics of speech signals (such as pronunciation accuracy, tone, stress, linking, assimilation, loss of plosives, intonation, and prosody) and behavioral characteristics (such as the use of vocabulary, grammar, and syntax at the language level).

[0049] This embodiment explains the process of judging whether an emotion is accurate and appropriate. It determines whether the spoken voice matches a preset emotion type based on preset sound parameters, including volume and amplitude. The preset emotion types include anger, happiness, and calmness. Based on these preset sound parameters, such as volume and amplitude, it is determined whether the voice matches emotions like "anger," "happiness," or "calmness."

[0050] In this embodiment, an NLP engine is used to train an NLP quality inspection model based on the intents (i.e., each knowledge point to be explained) and quality inspection rules in the explanation outline. After training, the model is loaded onto the instructor's terminal device. The instructor then turns on the terminal device and conducts the explanation normally. The terminal device records the audio and transmits the recording to the cloud in real time. The audio is then converted into text using ASR technology and fed into the NLP engine for understanding.

[0051] The NLP quality control model, based on established quality control logic, comprehensively evaluates the content of the presentation to determine whether it meets the requirements. Regarding the content, it utilizes NLP engine intent-matching technology to assess the adequacy of the explanation; and a spoken language assessment engine to evaluate aspects such as speaking speed and emotional expression. If content fails to meet the requirements, the omitted parts are recorded and sent to the presenter for inclusion in subsequent presentations; alternatively, the information can be pushed to the presenter's device in real-time, providing a reminder that a key point is missing and requesting the presenter to supplement it.

[0052] In summary, this invention configures a narration outline for each narration project, including pre-defined key points; it establishes narration quality inspection rules to judge the narration quality of key points, including whether the key points are correctly and accurately presented, the speaking speed, and the appropriateness of the narration's emotional expression; it trains the intentions and narration quality inspection rules within the narration outline to form an NLP quality inspection model; it acquires real-time narration recordings of the narrators and converts them into transcripts; it feeds the transcripts into the NLP quality inspection model for understanding and performs quality inspection on the narrators' real-time narration recordings. This invention enables the recording and evaluation of narrators' narration levels, avoids omitting key content, ensures the effectiveness of narration, and guarantees narration quality.

[0053] It should be noted that the method of this disclosure embodiment can be executed by a single device, such as a computer or server. The method of this embodiment can also be applied to a distributed scenario, where multiple devices cooperate to complete the task. In such a distributed scenario, one of these devices may execute only one or more steps of the method of this disclosure embodiment, and the multiple devices will interact with each other to complete the method described.

[0054] It should be noted that the above description describes some embodiments of this disclosure. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in a different order than that shown in the above embodiments and still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0055] Example 2

[0056] See Figure 2 Embodiment 2 of the present invention also provides a guide's explanation quality evaluation system, including:

[0057] The explanation outline configuration module 1 is used to configure the explanation outline for the explanation project. The explanation outline includes the key points of the explanation project that are preset.

[0058] The Quality Inspection Rule Configuration Module 2 is used to formulate the explanation quality inspection rules and judge the explanation of key points based on the explanation quality inspection rules. The explanation of key points includes whether the explanation of key points is correct and in place, the speed of the explanation, and whether the explanation of emotions is appropriate and in place.

[0059] The quality inspection model training module 3 is used to train the intentions and quality inspection rules involved in the explanation outline to form an NLP quality inspection model.

[0060] The audio recording acquisition module 4 is used to acquire the real-time audio recording of the narrator and convert the real-time audio recording into audio text.

[0061] The quality inspection and judgment module 5 is used to send the explanation text to the NLP quality inspection model for understanding, and to perform quality inspection and judgment on the real-time explanation recording of the explainer through the NLP quality inspection model.

[0062] In this embodiment, in the quality inspection rule configuration module 2, each knowledge point in the key points of the explanation is made into an intent using an NLP engine. If the explanation hits the specified intent, it is determined that the corresponding knowledge point has been explained. The number of hit intents is used to determine whether the specified key points of the explanation have been explained in place.

[0063] In this embodiment, the quality inspection rule configuration module 2 uses oral assessment technology. When the speech passes through the oral assessment engine, the oral assessment engine is used to determine the speaking speed. The speaking speed is compared with the preset speaking speed. When it exceeds the preset speaking speed threshold, the speaking speed is determined to be abnormal.

[0064] In this embodiment, the quality inspection rule configuration module 2 determines whether the explanation voice matches a preset emotion type based on preset sound parameters; the sound parameters include volume and amplitude; the preset emotion types include anger, happiness, and calmness.

[0065] In this embodiment, a missing point processing module 6 is also included, which is used to record and push the key points of the explanation that the guide misses, or to remind the guide in real time that the key points of the explanation are missing in a specified segment.

[0066] It should be noted that the information interaction and execution process between the modules / submodules of the above system are based on the same concept as the method embodiment in Embodiment 1 of this application, and the resulting technical effects are the same as those in the method embodiment of this application. For details, please refer to the description in the method embodiment shown above in this application, and it will not be repeated here.

[0067] Example 3

[0068] Embodiment 3 of the present invention provides a non-transitory computer-readable storage medium, wherein the computer-readable storage medium stores program code for an interpreter to explain a quality evaluation method, the program code including instructions for executing the interpreter's explanation of the quality evaluation method of Embodiment 1 or any possible implementation thereof.

[0069] Computer-readable storage media can be any available medium that a computer can access, or a data storage device such as a server or data center that integrates one or more available media. The available medium can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., DVDs), or semiconductor media (e.g., solid-state drives, SSDs).

[0070] Example 4

[0071] Embodiment 4 of the present invention provides an electronic device, including: a memory and a processor;

[0072] The processor and the memory communicate with each other via a bus; the memory stores program instructions that can be executed by the processor, and the processor can call the program instructions to execute the lecturer's explanation quality evaluation method of Embodiment 1 or any possible implementation thereof.

[0073] Specifically, a processor can be implemented in hardware or software. When implemented in hardware, the processor can be a logic circuit, an integrated circuit, etc. When implemented in software, the processor can be a general-purpose processor that reads software code stored in memory. This memory can be integrated into the processor or located outside the processor and exist independently.

[0074] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of the present invention are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means.

[0075] It is obvious to those skilled in the art that the modules or steps of the present invention described above can be implemented using general-purpose computing devices. They can be centralized on a single computing device or distributed across a network of multiple computing devices. Optionally, they can be implemented using computer-executable program code, thereby storing them in a storage device for execution by a computing device. In some cases, the steps shown or described can be performed in a different order than those presented herein, or they can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Thus, the present invention is not limited to any particular combination of hardware and software.

[0076] Although the present invention has been described in detail above with general descriptions and specific embodiments, modifications or improvements can be made to it, which will be obvious to those skilled in the art. Therefore, all such modifications or improvements made without departing from the spirit of the present invention fall within the scope of protection claimed by the present invention.

Claims

1. A method for evaluating the quality of a tour guide's explanation, characterized in that, include: In the wearable hardware device that combines edge and cloud and the data management system in the cloud, the explanation outline is configured for the explanation project. The explanation outline includes the key points of the explanation project that are preset. The explanation outline is configured with different focuses for different types of explanation projects. Establish quality inspection rules for explanations, and judge the explanation of key points based on these rules. The explanation of key points includes whether they are correctly and accurately explained, the pace of the explanation, and the appropriateness of the emotional tone. The content configuration includes whether a certain point is mentioned, whether the explanation of a certain point is sufficient and accurate, whether the points are explained correctly, the pace of the explanation, the emotional tone of the explanation, and whether there is interaction. The intentions and quality inspection rules mentioned in the outline are used to train an NLP quality inspection model through the BERT framework. Acquire real-time audio recordings of tour guides and convert them into written explanations. The text of the explanation is fed into the NLP quality inspection model for understanding, and the NLP quality inspection model is used to inspect and judge the real-time audio recording of the explanation. In the process of judging whether the explanation is adequate, each knowledge point in the key points of the explanation is made into an intent using an NLP engine. If the explanation hits the specified intent, it is determined that the corresponding knowledge point has been explained. The number of hits determines whether the key points of the explanation have been explained effectively. The explanation of the speaking speed judgment process uses oral assessment technology. When the voice passes through the oral assessment engine, the oral assessment engine is used to judge the speaking speed. The speaking speed is compared with the preset speaking speed. When the speaking speed exceeds the preset speaking speed threshold, the speaking speed is judged to be abnormal. The process of judging whether the explanation of emotions is correct and appropriate involves judging whether the explanation voice matches the preset emotion type based on preset voice parameters. Sound parameters include volume and amplitude; preset emotion types include anger, happiness, and calmness. The system records and pushes information on key points that the guides miss, or provides real-time reminders to guides that they may be missing pre-planned key points in specific segments.

2. A tour guide explanation quality evaluation system, employing the tour guide explanation quality evaluation method described in claim 1, characterized in that, include: The explanation outline configuration module is used to configure the explanation outline for the explanation project. The explanation outline includes the key points of the explanation project that are preset. The quality inspection rule configuration module is used to formulate the explanation quality inspection rules and judge the explanation of key points based on the explanation quality inspection rules. The explanation of key points includes whether the explanation of key points is correct and in place, the speed of the explanation, and whether the explanation of emotion is appropriate and in place. The quality inspection model training module is used to train the intentions and quality inspection rules involved in the explanation outline to form an NLP quality inspection model. The audio recording module is used to acquire real-time audio recordings of the narrator and convert them into audio text. The quality control module is used to feed the narration text into the NLP quality control model for understanding, and to perform quality control on the narrator's real-time narration recording through the NLP quality control model.

3. The tour guide explanation quality evaluation system according to claim 2, characterized in that, In the quality inspection rule configuration module, each knowledge point in the key points of the explanation is made into an intent using the NLP engine. If the explanation hits the specified intent, it is determined that the corresponding knowledge point has been explained. The number of hits determines whether the key points of the explanation have been explained effectively.

4. The tour guide explanation quality evaluation system according to claim 3, characterized in that, In the quality inspection rule configuration module, oral assessment technology is used. When the speech passes through the oral assessment engine, the oral assessment engine is used to determine the speaking speed. The speaking speed is compared with the preset speaking speed. When it exceeds the preset speaking speed threshold, the speaking speed is judged to be abnormal.

5. A tour guide explanation quality evaluation system according to claim 4, characterized in that, In the quality inspection rule configuration module, the system determines whether the narration voice matches the preset emotion type based on preset sound parameters. Sound parameters include volume and amplitude; preset emotion types include anger, happiness, and calmness.

6. The tour guide explanation quality evaluation system according to claim 2, characterized in that, It also includes a module for handling omissions, which records and pushes key points that the guide misses in the explanation, or reminds the guide in real time that there are no preset key points in the explanation in a certain segment.

Images