CN117853977A - Method, system, equipment and medium for intelligent evaluation through video - Google Patents
Method, system, equipment and medium for intelligent evaluation through video Download PDFInfo
- Publication number
- CN117853977A CN117853977A CN202410015043.0A CN202410015043A CN117853977A CN 117853977 A CN117853977 A CN 117853977A CN 202410015043 A CN202410015043 A CN 202410015043A CN 117853977 A CN117853977 A CN 117853977A
- Authority
- CN
- China
- Prior art keywords
- score
- evaluation
- target object
- video
- limb
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000011156 evaluation Methods 0.000 title claims abstract description 131
- 238000000034 method Methods 0.000 title claims abstract description 58
- 230000006399 behavior Effects 0.000 claims abstract description 71
- 230000009471 action Effects 0.000 claims abstract description 69
- 238000004458 analytical method Methods 0.000 claims abstract description 15
- 210000003414 extremity Anatomy 0.000 claims description 96
- 230000002159 abnormal effect Effects 0.000 claims description 30
- 230000008451 emotion Effects 0.000 claims description 18
- 210000003128 head Anatomy 0.000 claims description 16
- 238000012545 processing Methods 0.000 claims description 12
- 238000004364 calculation method Methods 0.000 claims description 10
- 238000005516 engineering process Methods 0.000 claims description 9
- 210000004709 eyebrow Anatomy 0.000 claims description 7
- 238000012512 characterization method Methods 0.000 claims description 5
- 238000013136 deep learning model Methods 0.000 claims description 5
- 230000000694 effects Effects 0.000 abstract description 4
- 238000012854 evaluation process Methods 0.000 abstract description 4
- 230000004044 response Effects 0.000 abstract description 2
- 230000036651 mood Effects 0.000 abstract 1
- 238000010586 diagram Methods 0.000 description 15
- 230000008569 process Effects 0.000 description 15
- 230000014509 gene expression Effects 0.000 description 10
- 238000004891 communication Methods 0.000 description 9
- 230000006870 function Effects 0.000 description 8
- 210000004204 blood vessel Anatomy 0.000 description 5
- 206010019233 Headaches Diseases 0.000 description 4
- 206010020772 Hypertension Diseases 0.000 description 4
- 230000036772 blood pressure Effects 0.000 description 4
- 210000004556 brain Anatomy 0.000 description 4
- 231100000869 headache Toxicity 0.000 description 4
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000033001 locomotion Effects 0.000 description 3
- 230000007246 mechanism Effects 0.000 description 3
- 230000005856 abnormality Effects 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 210000003205 muscle Anatomy 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 206010000117 Abnormal behaviour Diseases 0.000 description 1
- 206010063659 Aversion Diseases 0.000 description 1
- 208000003443 Unconsciousness Diseases 0.000 description 1
- 230000003542 behavioural effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000019771 cognition Effects 0.000 description 1
- 230000008602 contraction Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000002526 effect on cardiovascular system Effects 0.000 description 1
- 210000000744 eyelid Anatomy 0.000 description 1
- 230000008921 facial expression Effects 0.000 description 1
- 210000004247 hand Anatomy 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 235000012054 meals Nutrition 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000009877 rendering Methods 0.000 description 1
- 210000003813 thumb Anatomy 0.000 description 1
- 230000037303 wrinkles Effects 0.000 description 1
Landscapes
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
A method for intelligent evaluation through video relates to the field of evaluation. In the method, a video connection request is sent to a target object in response to an operation of sending an evaluation instruction by a user; when a target object receives a video connection request and passes identity authentication, playing questions in a preset evaluation table in a video mode, determining an answer result of the target object by collecting voice or limb description actions, acquiring multi-dimensional data of the target object when answering, and carrying out weighted summation according to the answer result and the multi-dimensional data to obtain a score of each question; and calculating to obtain the total score of all the topics according to the score of each topic, and matching a preset result according to the total score, wherein the result comprises a video analysis report or a text analysis report. By implementing the technical scheme provided by the application, the effect that the target object can independently complete the evaluation and record the behaviors and moods in the evaluation process is achieved.
Description
Technical Field
The application relates to the technical field of evaluation, in particular to a method, a system, electronic equipment and a storage medium for intelligent evaluation through videos.
Background
With the development of technology, the scale for assisting doctors is also continuously improved and perfected. Advances in technology have provided doctors with more tools and means to help them evaluate the health of patients more accurately.
The scale evaluation carried out on the market at present is mostly in the form of characters and pictures, the expression of the themes and the meanings is not very accurate, and the method is not friendly to low-culture people. And once a nurse or a third person of the family helps, the patient is easily disturbed and deviates from the theme. Moreover, the doctor only can see specific scores on the evaluation results, and the behaviors and emotions of the patient cannot be analyzed from the answering process, so that the scale cannot be accurately analyzed.
Therefore, there is a need for an evaluation method that can understand questions without the help of a third person and can record the behavior and emotion of a patient during a answering process.
Disclosure of Invention
The method can enable the answer objects to independently complete the evaluation and record the behavior and emotion of the answer objects in the evaluation process, so that doctors can take more targeted countermeasures according to the method.
In a first aspect of the present application, there is provided a method for performing intelligent assessment through video, applied to a medical management platform, the method comprising:
Responding to the operation of sending an evaluation instruction by a user, and sending a video connection request to a target object;
when a target object receives a video connection request and passes identity authentication, playing questions in a preset evaluation table in a video mode, and determining answer results of the target object by collecting voice or limb description actions, wherein the limb description actions comprise head swinging actions, the nodding represents affirmative, and the swinging represents negative;
obtaining multi-dimensional data of the target object during answering, and carrying out weighted summation according to the answering result and the multi-dimensional data to obtain a score of each question, wherein the multi-dimensional data comprises answering time, answering microexpressions and limb behaviors, the answering microexpressions comprise single or combined actions of eyes, mouth and eyebrows, and the limb behaviors comprise single or combined actions of hands and feet; and
and calculating to obtain the total score of all the topics according to the score of each topic, and matching a preset result according to the total score, wherein the result comprises a video analysis report or a text analysis report.
Through adopting above-mentioned technical scheme, use the video mode to carry out the evaluation, need not the interviewee personally to go to the evaluation scene, saved time and traffic cost, improved the convenience of evaluation, can avoid the subjective factor interference in the face-to-face communication, make the evaluation result objective fair more. The real ideas and behaviors of the interviewee can be more accurately estimated by collecting voice or limb description action to determine answer results, and the score of each question can be obtained by carrying out weighted summation on multidimensional data, so that the performance of the interviewee can be more comprehensively estimated. The total score of all the questions is obtained through calculation according to the score of each question, and the preset result is matched according to the total score, so that personalized evaluation reports can be provided according to the characteristics and requirements of different interviewees, and the pertinence and the effectiveness of evaluation are improved.
Optionally, the method further comprises:
and carrying out identity authentication on the target object in real time, and terminating answering when the target object is not detected or the identity authentication of the target object fails.
By adopting the technical scheme, invalid evaluation and data acquisition can be avoided, and the efficiency and accuracy of the evaluation are improved.
Optionally, playing the questions in the preset evaluation table in a video manner includes:
acquiring medical record data of the target object, and setting evaluation points according to abnormal items in the medical record data, wherein the abnormal items refer to data which are not in a preset range or abnormal characterization;
matching questions from a preset question library according to the abnormal items to generate an evaluation table, and setting weights corresponding to the questions in the evaluation table according to the evaluation key points;
and converting the title into pictures in voice and video and displaying the pictures to the target object.
By adopting the technical scheme, the actual condition of the target object can be evaluated, and the pertinence of the evaluation is improved. And generating an evaluation table from the matched questions in the preset question library according to the abnormal items, and setting the question weight according to the evaluation key points, so that the close correlation between the evaluated content and the actual condition of the target object can be ensured, and the evaluation accuracy is improved. The questions are converted into pictures in voice and video to be displayed to the target object, so that the evaluation is more visual and easier to understand, the evaluation forms are enriched, and the interest and participation of the evaluation are improved.
Optionally, the determining the answer result of the target object by collecting voice or limb description action includes:
extracting features in the voice by using a deep learning model, converting the features into corresponding texts, and matching corresponding answer results through the texts; and/or
And extracting the outline and the shape of the limb description action by using an image processing technology, matching a positive answer result when the limb description action is identified as nodding, and matching a negative answer result when the limb description action is identified as shaking.
By adopting the technical scheme, the characteristics in the voice are extracted, the characteristics are converted into the corresponding texts, and the answer results of the target object can be more accurately identified by matching the corresponding answer results with the texts. Meanwhile, the outline and the shape of the limb description action are extracted by using an image processing technology, so that the limb description action can be more accurately identified, and the accuracy of identifying the answering result is further improved.
Optionally, the obtaining the multidimensional data of the target object in answering includes:
acquiring a first answer time, and determining a first score of the first answer time from a preset answer time and score corresponding relation according to the first answer time;
Acquiring a first answer microexpression, acquiring corresponding emotion feedback from a microexpression recognition library according to the first answer microexpression, and determining a second score of the first answer microexpression from a preset emotion feedback and score corresponding relation according to the emotion feedback; and
acquiring a first limb behavior, acquiring corresponding behavior feedback from a limb behavior identification library according to the first limb behavior, and determining a third score of the first limb behavior from a preset corresponding relation between the behavior feedback and the score according to the behavior feedback.
By adopting the technical scheme, the multi-dimensional data of the target object in answering can be obtained, the performance of the target object can be evaluated more comprehensively, and more accurate and comprehensive basis is provided for the subsequent evaluation result. By matching the answer time, the answer microexpressions, the limb behaviors and other data with the preset score corresponding relation, the influence of subjective factors on the evaluation result can be avoided, and the objectivity and fairness of the evaluation are improved.
Optionally, the step of obtaining the score of each question by carrying out weighted summation according to the answer result and the multidimensional data includes:
and respectively calculating the products of the score, the first score, the second score and the third score of the answer result and the corresponding weight, and calculating the sum of the products as the score of the questions.
By adopting the technical scheme, the answer result and the multidimensional data are weighted and summed, so that various factors such as the answer result, the answer time, the answer microexpressions, the limb behaviors and the like can be comprehensively considered, and the answer result is comprehensively evaluated to obtain a more comprehensive and accurate score. By setting different weights, the weights of different evaluation dimensions can be balanced, so that the evaluation result is more reasonable and fair.
Optionally, the calculating the total score of all the topics according to the score of each topic includes:
obtaining the total score of all the questions according to the weighted summation of the weight of the questions and the score corresponding to the questions; or alternatively
The score for each topic is summed to obtain a total score for all topics.
By adopting the technical scheme, the importance and difficulty degree of different questions in the evaluation can be considered according to the weighted summation of the weights of the questions and the scores corresponding to the questions, so that a more reasonable and more accurate total score is obtained. By summing the scores of each topic, the calculation process can be simplified and the calculation efficiency can be improved.
In a second aspect of the present application, a system for performing intelligent assessment through video is provided, including a request module, an acquisition module, a calculation module, and a report module, wherein:
The request module is configured to respond to the operation of sending the evaluation instruction by the user and send a video connection request to the target object;
the acquisition module is configured to play the questions in a preset evaluation table in a video mode when a target object receives a video connection request and passes identity authentication, and determine the answer result of the target object by acquiring voice or limb description actions, wherein the limb description actions comprise hand and head swing actions, the nod head represents affirmative, and the swing head represents negative;
the computing module is configured to acquire multi-dimensional data of the target object during answering, and perform weighted summation according to the answering result and the multi-dimensional data to obtain a score of each question, wherein the multi-dimensional data comprises answering time, answering microexpressions and limb behaviors, the answering microexpressions comprise eye, mouth and eyebrow independent or combined actions, and the limb behaviors comprise hand and foot independent or combined actions; and
and the reporting module is configured to calculate and obtain the total score of all the topics according to the score of each topic, and match a preset result according to the total score, wherein the result comprises a video analysis report or a text analysis report.
In a third aspect the present application provides an electronic device comprising a processor, a memory for storing instructions, a user interface and a network interface, both for communicating with other devices, the processor being for executing the instructions stored in the memory to cause the electronic device to perform a method as claimed in any one of the preceding claims.
In a fourth aspect of the present application, there is provided a computer readable storage medium storing instructions that, when executed, perform a method as claimed in any one of the preceding claims.
In summary, one or more technical solutions provided in the embodiments of the present application at least have the following technical effects or advantages:
1. the evaluation is carried out in a video mode, and the multi-dimensional data such as the answer result, the answer time, the answer microexpressions, the limb behaviors and the like of the target object are combined for comprehensive evaluation, so that the accuracy and the comprehensiveness of the evaluation are improved;
2. the total score of all the questions is obtained through calculation according to the score of each question, and a preset result is matched according to the total score, so that a personalized evaluation report is provided, and the pertinence and the effectiveness of evaluation are improved;
3. By collecting and analyzing multidimensional data, richer data dimension can be provided for subsequent data analysis and mining, and data support is provided for decision making.
Drawings
Fig. 1 is a schematic flow chart of a method for performing intelligent evaluation through video according to an embodiment of the present application;
FIG. 2 is a schematic diagram of a main flow of a method for performing intelligent evaluation through video according to an embodiment of the present application;
FIG. 3 is a schematic diagram of matching patient information as disclosed in an embodiment of the present application;
fig. 4 is a schematic diagram of an answer process disclosed in an embodiment of the present application;
fig. 5 is a schematic diagram illustrating answer process judgment according to an embodiment of the present application;
FIG. 6 is a schematic illustration of microexpressive scoring as disclosed in the examples herein;
FIG. 7 is a schematic illustration of limb behavior scores disclosed in an embodiment of the present application;
FIG. 8 is a schematic diagram of evaluation according to weights as disclosed in the embodiments of the present application;
FIG. 9 is a block diagram of a system for intelligent assessment via video as disclosed in an embodiment of the present application;
fig. 10 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Reference numerals illustrate: 901. a request module; 902. an acquisition module; 903. a computing module; 904. a reporting module; 1001. a processor; 1002. a communication bus; 1003. a user interface; 1004. a network interface; 1005. a memory.
Detailed Description
In order to make those skilled in the art better understand the technical solutions in the present specification, the technical solutions in the embodiments of the present specification will be clearly and completely described below with reference to the drawings in the embodiments of the present specification, and it is obvious that the described embodiments are only some embodiments of the present application, but not all embodiments.
In the description of embodiments of the present application, words such as "for example" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described herein as "such as" or "for example" should not be construed as preferred or advantageous over other embodiments or designs. Rather, the use of words such as "or" for example "is intended to present related concepts in a concrete fashion.
In the description of the embodiments of the present application, the term "plurality" means two or more. For example, a plurality of systems means two or more systems, and a plurality of screen terminals means two or more screen terminals. Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating an indicated technical feature. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include one or more such feature. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless expressly specified otherwise.
The embodiment discloses a method for performing intelligent evaluation through video, and fig. 1 is a flow chart of the method for performing intelligent evaluation through video disclosed in the embodiment of the application, as shown in fig. 1, including the following steps:
s110, responding to the operation of sending an evaluation instruction by a user, and sending a video connection request to a target object;
s120, when a target object receives a video connection request and passes identity authentication, playing questions in a preset evaluation table in a video mode, and determining answer results of the target object by collecting voice or limb description actions, wherein the limb description actions comprise head swing actions, the nodding represents affirmative, and the swinging represents negative;
s130, acquiring multi-dimensional data of the target object in answering, and carrying out weighted summation according to the answering result and the multi-dimensional data to obtain a score of each question, wherein the multi-dimensional data comprises answering time, answering microexpressions and limb behaviors, the answering microexpressions comprise eye, mouth and eyebrow independent or combined actions, and the limb behaviors comprise hand and foot independent or combined actions; and
and S140, calculating to obtain the total score of all the topics according to the score of each topic, and matching a preset result according to the total score, wherein the result comprises a video analysis report or a text analysis report.
In the embodiment of the application, the doctor sends the video connection request to the patient as an example, and in other embodiments, the patient actively sends the video connection request to the doctor, or the third-party platform initiates the video connection request to the doctor and the patient at the same time. The video connection request may be encrypted by an encryption algorithm, which is not limited herein, and the patient or doctor may open the video connection request only by inputting a predetermined key, and may establish the video connection after the video connection request is opened.
When a patient opens a video connection request and passes identity authentication, playing the questions in a preset evaluation table in a video mode, expressing the self view of the patient through language or limb description actions, and determining the answer result of the patient through collecting voice or limb description actions, wherein the limb description actions comprise head swing actions, for example, head pointing represents affirmative and head swing represents negative; the limb descriptive action may also include a swinging action of the hand, e.g., a swinging hand signifying no, a thumb up signifying affirmative. In addition to obtaining the answer result of the patient, the multidimensional data of the patient during answer can be obtained, wherein the multidimensional data comprises answer time, answer microexpressions and limb behaviors, the microexpressions are short and unconscious facial expressions, and the production of the microexpressions comprises all muscle actions with exaggerated expressions or only partial muscle actions with exaggerated expressions. The composition is the same as that of the common expression, and comprises seven basic expressions: happiness, sadness, fear, aversion, surprise, anger and light. Answering micro-expressions include eye, mouth, eyebrow movements alone or in combination, such as tilting of the corners of the mouth, lifting of wrinkles on the cheeks, eyelid contraction may indicate pleasure. Limb behavior refers to a behavioral way of expressing emotion and transmitting information through body actions and gestures. Different limb behaviors can express different emotions and intentions. Limb behavior includes hand and foot motions alone or in combination. For example, a hammer table is an excessively abnormal limb behavior. And then carrying out weighted summation according to the answer result and the multidimensional data to obtain the score of each question.
The correspondence between the total score and the result may be preset, for example, the total score may be set to be greater than or equal to 80 and be excellent, the score may be greater than or equal to 60 and less than 80 is acceptable, the score may be less than 60 is unacceptable, and different analysis reports may be given for different scores.
Fig. 2 is a schematic diagram of a main flow of a method for performing intelligent evaluation through video according to an embodiment of the present application, where as shown in fig. 2, the main flow includes step 210 of establishing video connection between a doctor and a patient, and may actively initiate a video connection request through the doctor, may actively initiate a video connection request through the patient, and may also initiate video connection requests to the doctor and the patient respectively through a third party intelligent platform; 220, matching the automatic image recognition patient retrieval database to the patient after video connection; step 230, acquiring an evaluation scale video according to patient information; step 240, playing according to the preset video title of the database; step 250, judging whether the answer is finished or not according to the sound and the behaviors of the patient and judging the next question; and 260, collecting answer results, answer time and answer behaviors of each question after the evaluation is finished, and reporting according to the weight.
Through the video mode, the patient can express own views through language or limb description actions, the interactivity and participation degree with the system are enhanced, and the evaluation process is more natural and smooth. The method has the advantages that the answer result of the patient is determined by collecting voice or limb description actions, the intention and the answer of the patient can be more accurately identified, and the accuracy of the answer result is improved. Through obtaining the multidimensional data of the patient during answering, including answering time, answering microexpressions and limb behaviors, the performance of the patient can be evaluated more comprehensively, and more accurate data support is provided for subsequent medical management. The answer result and the multidimensional data are weighted and summed to obtain the score of each question, so that the influence of subjective factors on the evaluation result can be avoided, and the objectivity and fairness of evaluation are improved.
Optionally, the method further comprises:
and carrying out identity authentication on the target object in real time, and terminating answering when the target object is not detected or the identity authentication of the target object fails.
Referring to fig. 2, in the video evaluation process, the method further includes step 201, in which the person image recognition detects that the person image of the patient is restored, and the evaluation is automatically continued; step 202, the person image recognition detects that the person image of the patient is changed or lost, and the evaluation is automatically stopped. In order to test the reality and accuracy of the result, can carry on the identity authentication to the goal object in real time, avoid other people to replace the goal object to test.
FIG. 3 is a schematic diagram of matching patient information disclosed in an embodiment of the present application, as shown in FIG. 3, the matching patient information includes a step 301, and video evaluation begins; step 302, capturing a face picture of a patient; step 303, adopting face recognition to match to a patient; or step 304, speech dictation identity feature identification; step 305, matching the patient library to confirm the patient; after the patient is identified, step 306, precisely matching the patient may be performed; then, step 307 is performed to acquire information to be evaluated.
By carrying out identity authentication on the target object in real time, only legal users can participate in answering, the situation that illegal users impersonate or replace the target object to answer is avoided, and the validity and fairness of answering are guaranteed. In the scenes such as medical management platform, the method relates to sensitive information and privacy protection, and the real-time identity authentication of the target object can ensure that only authorized personnel can access and operate related data, so that the safety and reliability of the system are improved. When the target object cannot be detected or the identity authentication of the target object fails, the answer is terminated, invalid answer and data acquisition can be avoided, the efficiency and the accuracy of the system are improved, and meanwhile, the user experience is enhanced.
Optionally, playing the questions in the preset evaluation table in a video manner includes:
acquiring medical record data of the target object, and setting evaluation points according to abnormal items in the medical record data, wherein the abnormal items refer to data which are not in a preset range or abnormal characterization;
matching questions from a preset question library according to the abnormal items to generate an evaluation table, and setting weights corresponding to the questions in the evaluation table according to the evaluation key points;
and converting the title into pictures in voice and video and displaying the pictures to the target object.
Obtaining medical record data of a patient, and setting evaluation points through abnormal items in the medical record data, for example, the abnormal items in the medical record data are hypertension and headache, the hypertension belongs to data which are not in a preset range, and the headache belongs to abnormal characterization. If there is a correlation between the abnormal items, one evaluation point may be determined according to the abnormality, and if there is no correlation between the abnormal items, a plurality of evaluation points may be determined. In the embodiment of the application, the evaluation key point can be set according to the hypertension and headache and is the cardiovascular and cerebrovascular blood vessels. The questions in terms of blood pressure can be matched from a preset question bank according to the abnormal term of the hypertension, and the questions in terms of brain and blood vessels can be matched from the preset question bank according to the abnormal term of headache. The weight corresponding to the subject in the evaluation table is set according to the evaluation point, for example, the weight of the subject in terms of blood pressure, the weight of the subject in terms of brain and blood vessel, and the weight of the remaining common sense subjects are set to be 40%. And converting the set questions into pictures in voice and video to be displayed to the patient.
Fig. 4 is a schematic diagram of an answer process disclosed in an embodiment of the present application, as shown in fig. 4, where the answer process includes a step 401, and a patient may start to issue after being ready; step 402, acquiring a first evaluation question; step 403, playing the title through video and voice; step 404, judging that the answer is ended according to the oral or action of the patient; step 405, recording answering voices, time, micro expressions and limb behaviors; then, a second evaluation question is acquired, and the steps 403-405 are repeated until all questions are processed; step 406, collecting all answer information of the evaluation; step 407, calculating an evaluation result according to the weight according to the answering voice, time, micro expression and limb behaviors; step 408, generating a report according to the result.
By acquiring medical record data of the target object and setting evaluation points according to abnormal items in the medical record data, personalized evaluation can be performed on specific conditions of each patient, and pertinence and effectiveness of the evaluation are improved. According to the abnormal item, the questions are matched from the preset question library to generate an evaluation table, so that the evaluation questions can be ensured to be matched with the actual condition of the patient, the questions which are not related to the actual condition of the patient are avoided, and the accuracy and pertinence of the evaluation are improved. The weights corresponding to the questions in the evaluation table are set according to the evaluation key points, and the weights can be flexibly adjusted according to the importance degrees of different questions, so that the evaluation result is more reasonable and fair. The questions are converted into pictures in voice and video to be displayed to the target object, a more visual and vivid evaluation mode can be provided, and the participation degree and evaluation effect of patients are improved.
Optionally, the determining the answer result of the target object by collecting voice or limb description action includes:
extracting features in the voice by using a deep learning model, converting the features into corresponding texts, and matching corresponding answer results through the texts; and/or
And extracting the outline and the shape of the limb description action by using an image processing technology, matching a positive answer result when the limb description action is identified as nodding, and matching a negative answer result when the limb description action is identified as shaking.
Fig. 5 is a schematic diagram illustrating answer process judgment disclosed in the embodiment of the present application, as shown in fig. 5, after a patient is ready to start preparing for answering, triggering step 501, and starting a video answer judgment mechanism; executing step 502, video playing and evaluating questions; executing step 503 or 505, wherein step 503 is to identify a matching action according to the human body, and step 504 is a specific matched action, for example, the title is that you eat, the nod indicates eating, and the shake indicates not eating; step 505 is to parse the spoken matching answer and step 506 is to match a specific answer, e.g., do you eat the question, the patient says "i eat" may indicate that he eat the meal, and the patient says "not eat" indicates that he has not yet eaten. When the answer is determined, step 507 may be performed to determine that the answer is completed for the current question. When the speech recognized answer conflicts with the action recognized answer, the patient is prompted to answer again.
By extracting features in the voice by using the deep learning model and converting the features into corresponding texts, automatic conversion from voice to texts can be realized. The system can accurately identify and understand the answer of the target object, and the accuracy and the readability of the answer are improved. By extracting the outline and shape of the limb description action by using an image processing technology, simple limb actions such as nodding and waving can be identified. The system can infer the answer of the target object according to the limb action of the target object, and provides another effective answer mode for the target object which can not communicate by using language. By using the voice recognition and limb action recognition technology simultaneously, the system can acquire the answers of the target object from multiple dimensions and can more comprehensively and accurately match corresponding answer results. This improves the accuracy and reliability of the answer, enabling the system to evaluate the performance of the target object more effectively.
Optionally, the obtaining the multidimensional data of the target object in answering includes:
acquiring a first answer time, and determining a first score of the first answer time from a preset answer time and score corresponding relation according to the first answer time;
Acquiring a first answer microexpression, acquiring corresponding emotion feedback from a microexpression recognition library according to the first answer microexpression, and determining a second score of the first answer microexpression from a preset emotion feedback and score corresponding relation according to the emotion feedback; and
acquiring a first limb behavior, acquiring corresponding behavior feedback from a limb behavior identification library according to the first limb behavior, and determining a third score of the first limb behavior from a preset corresponding relation between the behavior feedback and the score according to the behavior feedback.
The answering time refers to the time from the sending of an instruction of starting answering to the obtaining of the answer of the patient, the matching relation between the answering time and the corresponding score is preset, and the corresponding score can be obtained from the matching relation according to the answering time.
Fig. 6 is a schematic diagram of a micro-expression score disclosed in the embodiment of the present application, as shown in fig. 6, where the micro-expression score includes a step 601 and a trigger answer micro-expression judgment mechanism; step 602, capturing micro expressions of a video process; step 603, matching a micro expression recognition library; step 604, obtaining a matching result of the micro-expressions; step 605, determining a corresponding score according to the matching result (passive, active, surprise, ambiguous).
Fig. 7 is a schematic diagram of limb behavior scoring disclosed in the embodiment of the present application, as shown in fig. 7, where the limb behavior scoring includes a step 701, and a trigger answer limb behavior mechanism; step 702, analyzing the video limb actions; step 703, matching a limb identification library; step 704, obtaining a limb behavior result; step 705, determining corresponding scores according to limb behavior results (normal, abnormal, excessive abnormal). Excessive anomalies are expressed as dangerous behavior present, such as: handling dangerous objects, head crashing walls, etc., abnormal behavior is expressed as the presence of abnormal limb movements, such as: the people can get tired when answering questions, and the limbs can act excessively.
The performance of the target object can be more comprehensively evaluated by acquiring multidimensional data of the target object during answering, including answering time, answering microexpressions and limb behaviors. The comprehensive evaluation mode can reflect the cognition, emotion and behavior states of the target object more accurately, and provides more accurate data support for subsequent medical management. By matching the answering time, the answering microexpressions and the limb behaviors with the preset corresponding relations, the influence of subjective factors on the evaluation result can be avoided, and the objectivity and fairness of the evaluation are improved. The objective and fair evaluation mode can provide more accurate feedback and advice for patients, and is helpful for improving the effect of medical management. And comprehensively evaluating the multi-dimensional data according to the answering time, the answering microexpressions, the limb behaviors and the like of the target object, and providing personalized evaluation results for each patient. The personalized evaluation mode can better meet the needs of patients and improve the pertinence and the effectiveness of medical management.
Optionally, the step of obtaining the score of each question by carrying out weighted summation according to the answer result and the multidimensional data includes:
and respectively calculating the products of the score, the first score, the second score and the third score of the answer result and the corresponding weight, and calculating the sum of the products as the score of the questions.
FIG. 8 is a schematic diagram of evaluation according to weights according to the embodiment of the present application, as shown in FIG. 8, when a topic ends, step 801 is executed to match corresponding scores according to spoken answers or limb answers; step 802, comparing the spoken answer or the limb answer with a preset corresponding relation to determine a corresponding score, for example, 10 scores are corresponding to happiness; 803, determining that the weight of the question answer is 40%; step 804, multiplying the weights and the scores to obtain corresponding scores, for example, 10 scores by 40% = 4 scores; simultaneously executing step 805, matching corresponding scores according to answering time; step 806, comparing the answer time with a preset corresponding relation to determine a corresponding score, for example, the answer time corresponds to 8 seconds and is 6 scores; step 807, determining that the weight of the question answer is 20%; step 808, multiplying the weights and the scores to obtain corresponding scores, for example, 6 scores by 20% = 1.2 scores; step 809 is executed simultaneously, and corresponding scores are matched according to the micro expression condition; step 810, comparing the microexpressive situation with a preset corresponding relation to determine a corresponding score, for example, a score of 10 is positively corresponding; step 811, determining that the weight of the question answer is 20%; step 812, multiplying the weights and the scores to obtain corresponding scores, for example, 10 scores by 20% = 2 scores; step 813, matching the corresponding scores according to the limb behaviors; step 814, comparing the limb behavior with a preset corresponding relationship to determine a corresponding score, for example, 5 scores are corresponding to the abnormality; step 815, determining that the weight of the question answer is 20%; step 816, multiplying the weights and the scores to obtain corresponding scores, for example, 5 scores by 20% = 1 score; executing step 817, and summarizing all scores of the topics; step 818 is performed to feed back the result.
The combined score for each question may be obtained by weighted summing the answer result, the first score, the second score, and the third score with corresponding weights. The comprehensive evaluation mode can comprehensively consider the performances of the target object in multiple aspects in the answering process, so that a more comprehensive and accurate score is obtained. By setting different weights, the evaluation emphasis can be adjusted according to the importance degree or evaluation emphasis point of different questions. The flexibility of the weight adjustment can better meet the evaluation requirements under different scenes, and the pertinence and the effectiveness of the evaluation are improved. By calculating the product of the score of each dimension and the corresponding weight, and calculating the sum of the products as the score of the topic, the accuracy and fairness of the score can be ensured. The score calculation mode can avoid the influence of subjective factors on the score, and improves the objectivity and fairness of evaluation. Based on the results of the target object's answers and the multidimensional data, a personalized assessment score may be provided for each patient. The personalized evaluation mode can better meet the needs of patients and improve the pertinence and the effectiveness of medical management.
Optionally, the calculating the total score of all the topics according to the score of each topic includes:
Obtaining the total score of all the questions according to the weighted summation of the weight of the questions and the score corresponding to the questions; or alternatively
The score for each topic is summed to obtain a total score for all topics.
Weights can be set for each question, for example, 10 questions in total, 4 questions about blood pressure, 4 questions about brain and blood vessels and 2 common sense questions can be set; the weight of the questions about blood pressure can be set higher, for example, 12%, and the questions about brain and blood vessels can be set to 12%, and the weight of each general knowledge question can be set to 2%. The total score of all topics is obtained by weighting calculation in this way. Alternatively, the scores of each topic are directly added to give a total score.
The combined total score for all topics may be obtained by weighted summing the score for each topic with the weight for the corresponding topic. The comprehensive evaluation mode can comprehensively consider the overall performance of the target object in the answering process, so that a more comprehensive and more accurate total score is obtained. By setting different topic weights, the method can be adjusted according to the importance degree or evaluation emphasis point of different topics. The flexibility of the weight adjustment can better meet the evaluation requirements under different scenes, and the pertinence and the effectiveness of the evaluation are improved. By summing the scores of each topic to obtain a total score for all topics, the accuracy and fairness of the total score can be ensured. The total score calculation mode can avoid the influence of subjective factors on the total score, and improves the objectivity and fairness of evaluation. By comparing and analyzing the total scores of different questions or different patients, the performance difference of the target object in the answering process can be better known, and more accurate data support is provided for subsequent medical management.
The embodiment also discloses a system for performing intelligent evaluation through video, and fig. 9 is a schematic block diagram of the system for performing intelligent evaluation through video disclosed in the embodiment of the present application, as shown in fig. 9, the system includes a request module 901, an acquisition module 902, a calculation module 903, and a report module 904, where:
a request module 901, configured to send a video connection request to a target object in response to an operation of sending an evaluation instruction by a user;
the acquisition module 902 is configured to play a question in a preset evaluation table in a video mode when a target object receives a video connection request and passes identity authentication, and determine a question answering result of the target object by acquiring voice or limb description actions, wherein the limb description actions comprise hand and head swing actions, a nod head represents affirmative, and a swing head represents negative;
the computing module 903 is configured to obtain multidimensional data of the target object during answering, and perform weighted summation according to the answering result and the multidimensional data to obtain a score of each question, where the multidimensional data includes answering time, answering microexpressions and limb behaviors, the answering microexpressions include eye, mouth and eyebrow, and the limb behaviors include hand and foot, respectively; and
The reporting module 904 is configured to calculate a total score of all topics according to the score of each topic, and match a preset result according to the total score, where the result includes a video analysis report or a text analysis report.
Optionally, the system further comprises an authentication module configured to:
and carrying out identity authentication on the target object in real time, and terminating answering when the target object is not detected or the identity authentication of the target object fails.
Optionally, the acquisition module 902 is further configured to:
acquiring medical record data of the target object, and setting evaluation points according to abnormal items in the medical record data, wherein the abnormal items refer to data which are not in a preset range or abnormal characterization;
matching questions from a preset question library according to the abnormal items to generate an evaluation table, and setting weights corresponding to the questions in the evaluation table according to the evaluation key points;
and converting the title into pictures in voice and video and displaying the pictures to the target object.
Optionally, the acquisition module 902 is configured to:
extracting features in the voice by using a deep learning model, converting the features into corresponding texts, and matching corresponding answer results through the texts; and/or
And extracting the outline and the shape of the limb description action by using an image processing technology, matching a positive answer result when the limb description action is identified as nodding, and matching a negative answer result when the limb description action is identified as shaking.
Optionally, the computing module 903 is configured to:
acquiring a first answer time, and determining a first score of the first answer time from a preset answer time and score corresponding relation according to the first answer time;
acquiring a first answer microexpression, acquiring corresponding emotion feedback from a microexpression recognition library according to the first answer microexpression, and determining a second score of the first answer microexpression from a preset emotion feedback and score corresponding relation according to the emotion feedback; and
acquiring a first limb behavior, acquiring corresponding behavior feedback from a limb behavior identification library according to the first limb behavior, and determining a third score of the first limb behavior from a preset corresponding relation between the behavior feedback and the score according to the behavior feedback.
Optionally, the computing module 903 is further configured to:
and respectively calculating the products of the score, the first score, the second score and the third score of the answer result and the corresponding weight, and calculating the sum of the products as the score of the questions.
Optionally, the reporting module 904 is configured to:
obtaining the total score of all the questions according to the weighted summation of the weight of the questions and the score corresponding to the questions; or alternatively
The score for each topic is summed to obtain a total score for all topics.
It should be noted that: in the device provided in the above embodiment, when implementing the functions thereof, only the division of the above functional modules is used as an example, in practical application, the above functional allocation may be implemented by different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules, so as to implement all or part of the functions described above. In addition, the embodiments of the apparatus and the method provided in the foregoing embodiments belong to the same concept, and specific implementation processes of the embodiments of the method are detailed in the method embodiments, which are not repeated herein.
The embodiment also discloses an electronic device, referring to fig. 10, the electronic device may include: at least one processor 1001, at least one communication bus 1002, a user interface 1003, a network interface 1004, at least one memory. 1005
Wherein the communication bus 1002 is used to enable connected communication between these components.
The user interface 1003 may include a Display screen (Display) and a Camera (Camera), and the optional user interface 1003 may further include a standard wired interface and a wireless interface.
The network interface 1004 may optionally include a standard wired interface, a wireless interface (e.g., WI-FI interface), among others.
Wherein the processor 1001 may include one or more processing cores. The processor 1001 connects various parts within the entire server using various interfaces and lines, performs various functions of the server and processes data by executing or executing instructions, programs, code sets, or instruction sets stored in the memory, and calling data stored in the memory. Alternatively, the processor 1001 may be implemented in at least one hardware form of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), programmable logic array (Programmable Logic Array, PLA). The processor 1001 may integrate one or a combination of several of a central processor 1001 (Central Processing Unit, CPU), an image processor 1001 (Graphics Processing Unit, GPU), and a modem, etc. The CPU mainly processes an operating system, a user interface, an application program and the like; the GPU is used for rendering and drawing the content required to be displayed by the display screen; the modem is used to handle wireless communications. It will be appreciated that the modem may not be integrated into the processor 1001 and may be implemented by a single chip.
The Memory may include a random access Memory (Random Access Memory, RAM) or a Read-Only Memory (Read-Only Memory). Optionally, the memory includes a non-transitory computer readable medium (non-transitory computer-readable storage medium). The memory may be used to store instructions, programs, code sets, or instruction sets. The memory may include a stored program area and a stored data area, wherein the stored program area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playing function, an image playing function, etc.), instructions for implementing the above-described respective method embodiments, etc.; the storage data area may store data or the like involved in the above respective method embodiments. The memory may optionally also be at least one storage device located remotely from the processor 1001. As shown in fig. 10, an operating system, a network communication module, a user interface module, and an application program of a method of evaluating by video may be included in a memory as one type of computer storage medium.
In the electronic device shown in fig. 10, the user interface 1003 is mainly used for providing an input interface for a user, and acquiring data input by the user; and the processor 1001 may be configured to invoke an application in memory that stores methods of evaluating via video, which when executed by the one or more processors 1001, causes the electronic device to perform the methods as in one or more of the embodiments described above.
It should be noted that, for simplicity of description, the foregoing method embodiments are all expressed as a series of action combinations, but it should be understood by those skilled in the art that the present application is not limited by the order of actions described, as some steps may be performed in other order or simultaneously in accordance with the present application. Further, those skilled in the art will also appreciate that the embodiments described in the specification are all preferred embodiments, and that the acts and modules referred to are not necessarily required in the present application.
In the foregoing embodiments, the descriptions of the embodiments are emphasized, and for parts of one embodiment that are not described in detail, reference may be made to related descriptions of other embodiments.
In the several embodiments provided herein, it should be understood that the disclosed apparatus may be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative, such as a division of units, merely a division of logic functions, and there may be additional divisions in actual implementation, such as multiple units or components may be combined or integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be through some service interface, device or unit indirect coupling or communication connection, electrical or otherwise.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed over a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in each embodiment of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.
The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable memory. Based on such understanding, the technical solution of the present application may be embodied in essence or a part contributing to the prior art or all or part of the technical solution in the form of a software product stored in a memory, including several instructions for causing a computer device (which may be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the methods of the embodiments of the present application. And the aforementioned memory includes: various media capable of storing program codes, such as a U disk, a mobile hard disk, a magnetic disk or an optical disk.
The foregoing is merely exemplary embodiments of the present disclosure and is not intended to limit the scope of the present disclosure. That is, equivalent changes and modifications are contemplated by the teachings of this disclosure, which fall within the scope of the present disclosure. Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure. This application is intended to cover any adaptations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a scope and spirit of the disclosure being indicated by the claims.
Claims (10)
1. A method for intelligent assessment through video, which is applied to a medical management platform, the method comprising:
responding to the operation of sending an evaluation instruction by a user, and sending a video connection request to a target object;
when a target object receives a video connection request and passes identity authentication, playing questions in a preset evaluation table in a video mode, and determining answer results of the target object by collecting voice or limb description actions, wherein the limb description actions comprise head swinging actions, the nodding represents affirmative, and the swinging represents negative;
Obtaining multi-dimensional data of the target object during answering, and carrying out weighted summation according to the answering result and the multi-dimensional data to obtain a score of each question, wherein the multi-dimensional data comprises answering time, answering microexpressions and limb behaviors, the answering microexpressions comprise single or combined actions of eyes, mouth and eyebrows, and the limb behaviors comprise single or combined actions of hands and feet; and
and calculating to obtain the total score of all the topics according to the score of each topic, and matching a preset result according to the total score, wherein the result comprises a video analysis report or a text analysis report.
2. The method for intelligent assessment via video according to claim 1, further comprising:
and carrying out identity authentication on the target object in real time, and terminating answering when the target object is not detected or the identity authentication of the target object fails.
3. The method for intelligently evaluating through video according to claim 1, wherein playing the questions in the preset evaluation table through the video comprises:
acquiring medical record data of the target object, and setting evaluation points according to abnormal items in the medical record data, wherein the abnormal items refer to data which are not in a preset range or abnormal characterization;
Matching questions from a preset question library according to the abnormal items to generate an evaluation table, and setting weights corresponding to the questions in the evaluation table according to the evaluation key points;
and converting the title into pictures in voice and video and displaying the pictures to the target object.
4. The method for intelligent evaluation through video according to claim 1, wherein the determining the answer result of the target object by collecting voice or limb description actions comprises:
extracting features in the voice by using a deep learning model, converting the features into corresponding texts, and matching corresponding answer results through the texts; and/or
And extracting the outline and the shape of the limb description action by using an image processing technology, matching a positive answer result when the limb description action is identified as nodding, and matching a negative answer result when the limb description action is identified as shaking.
5. The method for intelligent evaluation through video according to claim 1, wherein the obtaining multidimensional data of the target object in answering comprises:
acquiring a first answer time, and determining a first score of the first answer time from a preset answer time and score corresponding relation according to the first answer time;
Acquiring a first answer microexpression, acquiring corresponding emotion feedback from a microexpression recognition library according to the first answer microexpression, and determining a second score of the first answer microexpression from a preset emotion feedback and score corresponding relation according to the emotion feedback; and
acquiring a first limb behavior, acquiring corresponding behavior feedback from a limb behavior identification library according to the first limb behavior, and determining a third score of the first limb behavior from a preset corresponding relation between the behavior feedback and the score according to the behavior feedback.
6. The method for intelligent evaluation through video according to claim 5, wherein the step of performing weighted summation according to the answer result and the multidimensional data to obtain a score of each question comprises:
and respectively calculating the products of the score, the first score, the second score and the third score of the answer result and the corresponding weight, and calculating the sum of the products as the score of the questions.
7. The method for intelligent evaluation through video according to claim 3, wherein the calculating the total score of all topics according to the score of each topic comprises:
obtaining the total score of all the questions according to the weighted summation of the weight of the questions and the score corresponding to the questions; or alternatively
The score for each topic is summed to obtain a total score for all topics.
8. The system for intelligent evaluation through video is characterized by comprising a request module, an acquisition module, a calculation module and a report module, wherein:
the request module is configured to respond to the operation of sending the evaluation instruction by the user and send a video connection request to the target object;
the acquisition module is configured to play the questions in a preset evaluation table in a video mode when a target object receives a video connection request and passes identity authentication, and determine the answer result of the target object by acquiring voice or limb description actions, wherein the limb description actions comprise hand and head swing actions, the nod head represents affirmative, and the swing head represents negative;
the computing module is configured to acquire multi-dimensional data of the target object during answering, and perform weighted summation according to the answering result and the multi-dimensional data to obtain a score of each question, wherein the multi-dimensional data comprises answering time, answering microexpressions and limb behaviors, the answering microexpressions comprise eye, mouth and eyebrow independent or combined actions, and the limb behaviors comprise hand and foot independent or combined actions; and
And the reporting module is configured to calculate and obtain the total score of all the topics according to the score of each topic, and match a preset result according to the total score, wherein the result comprises a video analysis report or a text analysis report.
9. An electronic device comprising a processor, a memory, a user interface, and a network interface, the memory for storing instructions, the user interface and the network interface each for communicating with other devices, the processor for executing instructions stored in the memory to cause the electronic device to perform the method of any of claims 1-7.
10. A computer readable storage medium storing instructions which, when executed, perform the method of any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410015043.0A CN117853977A (en) | 2024-01-04 | 2024-01-04 | Method, system, equipment and medium for intelligent evaluation through video |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410015043.0A CN117853977A (en) | 2024-01-04 | 2024-01-04 | Method, system, equipment and medium for intelligent evaluation through video |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117853977A true CN117853977A (en) | 2024-04-09 |
Family
ID=90543309
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410015043.0A Pending CN117853977A (en) | 2024-01-04 | 2024-01-04 | Method, system, equipment and medium for intelligent evaluation through video |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117853977A (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109872026A (en) * | 2018-12-14 | 2019-06-11 | 深圳壹账通智能科技有限公司 | Evaluation result generation method, device, equipment and computer readable storage medium |
| CN112836691A (en) * | 2021-03-31 | 2021-05-25 | 中国工商银行股份有限公司 | Intelligent interviewing method and device |
| CN113034044A (en) * | 2021-04-20 | 2021-06-25 | 平安科技（深圳）有限公司 | Interviewing method, device, equipment and medium based on artificial intelligence |
-
2024
- 2024-01-04 CN CN202410015043.0A patent/CN117853977A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109872026A (en) * | 2018-12-14 | 2019-06-11 | 深圳壹账通智能科技有限公司 | Evaluation result generation method, device, equipment and computer readable storage medium |
| CN112836691A (en) * | 2021-03-31 | 2021-05-25 | 中国工商银行股份有限公司 | Intelligent interviewing method and device |
| CN113034044A (en) * | 2021-04-20 | 2021-06-25 | 平安科技（深圳）有限公司 | Interviewing method, device, equipment and medium based on artificial intelligence |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR102277820B1 (en) | The psychological counseling system and the method thereof using the feeling information and response information | |
| US10376197B2 (en) | Diagnosing system for consciousness level measurement and method thereof | |
| US20220392625A1 (en) | Method and system for an interface to provide activity recommendations | |
| CN102149319B (en) | Alzheimer's cognitive enabler | |
| CN111724882A (en) | System and method for training psychology of friend-already based on virtual reality technology | |
| US20210192221A1 (en) | System and method for detecting deception in an audio-video response of a user | |
| US20220369973A1 (en) | Extended reality system to treat subjects associated with autism spectrum disorder | |
| CN116661607A (en) | Emotion adjustment method and system based on multi-modal emotion interaction | |
| KR102670492B1 (en) | Method and apparatus for psychological counselingusing artificial intelligence | |
| Mavromoustakos-Blom et al. | Personalized crisis management training on a tablet | |
| CN116935480B (en) | Emotion recognition method and device | |
| US11543884B2 (en) | Headset signals to determine emotional states | |
| CN117853977A (en) | Method, system, equipment and medium for intelligent evaluation through video | |
| US10820851B2 (en) | Diagnosing system for consciousness level measurement and method thereof | |
| Nakagawa et al. | A telecare system that estimates quality of life through communication | |
| Ferrari et al. | Using voice and biofeedback to predict user engagement during product feedback interviews | |
| CN112185516A (en) | Human-computer interaction based mental construction method and device for heavy smart personnel and electronic equipment | |
| WO2020141977A1 (en) | System and method of obtaining authentication information for user input information | |
| CN118335123A (en) | Method, system, equipment and medium for intelligent evaluation through communication | |
| Bahreini et al. | FILTWAM and voice emotion recognition | |
| KR102610267B1 (en) | Method for analyzing status of specific user corresponding to specific avatar by referring to interactions between the specific avatar and other avatars in the metaverse world and providing service to the specific user and device using the same | |
| US20230099519A1 (en) | Systems and methods for managing stress experienced by users during events | |
| US20240032833A1 (en) | Systems and methods for assessment in virtual reality therapy | |
| Tu et al. | The Effect of Two Different Types of Human-Computer Interactions on User's Emotion in Virtual Counseling Environment | |
| Manjunatha et al. | Quality of Life Estimation Using a Convolutional Neural Network Technique |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |