Online medical community multi-information importance evaluation method based on eye movement technology

Abstract

The invention discloses an online medical community multi-information importance evaluation method based on an eye movement technology. The method comprises the following steps: dividing multi-information in an online medical community into doctor generation information, patient generation information and platform generation information; dividing regions of interest of an online medical community doctor homepage based on the doctor generation information, the patient generation information and the platform generation information, obtaining eye movement data of each region of interest, and performing data preprocessing; calculating the total gazing time length, the average gazing time length and the unit average gazing time length of each region of interest; calculating the total number of fixation points, the average number of fixation points and the unit average number of fixation points of each region of interest; calculating the attention based on the unit average fixation duration and the unit average fixation point number; and obtaining an online medical community multi-information importance evaluation result based on the attention of different information areas. According to the method, the real information attention tendency of the user can be accurately captured, and online medical community multi-information importance evaluation is realized.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of eye tracking, in particular to an online medical community multi-information importance evaluation method based on eye tracking technology. BACKGROUND

[0002] In recent years, with the in-depth application of Internet technology in the medical field, online medical communities have gradually become an important bridge connecting patients and medical resources. In the traditional medical scene, patients are often limited by their place of residence and time for medical treatment, especially in remote areas, and it is difficult for them to access high-quality medical resources in a timely manner, which has exacerbated the imbalance in the development of medical services between urban and rural areas and regions. Online medical communities, through online platforms, allow patients to communicate with doctors about health problems and obtain professional advice without leaving home, greatly reducing the time and space costs of medical treatment, and allowing more people to conveniently enjoy the medical services they need. Users can form an overall impression of the professionalism and service quality of doctors by browsing the multi-information on the doctor's homepage before consultation, and then choose the appropriate doctor to meet their needs for health consultation; Currently, there is a large difference in the number of consultations for different doctors in online medical communities, and the information presented in different doctor homepages is one of the important reasons. It is necessary to understand the factors that users really pay attention to when choosing doctors online and the differences in attention to different information. Online medical communities are a typical multi-agent service mode, filled with various information, but the influence of multi-information in online medical communities has not been fully explored. The main defects and deficiencies of existing methods and research are: first, traditional information importance evaluation mainly relies on questionnaire surveys, which is easily affected by user subjective factors, resulting in inaccurate evaluation results; second, existing eye tracking technology is mainly used for advertising effect evaluation, and has not been widely applied in online medical systems. SUMMARY

[0003] In order to overcome the defects and deficiencies of the prior art, the present application provides an online medical community multi-information importance evaluation method based on eye tracking technology. According to the participants in the online medical community, namely doctors, patients and platform, the multi-information in the online medical community is divided accordingly. Specifically, the multi-information in the online medical community is divided into doctor-generated information, patient-generated information and platform-generated information. The present application focuses on the three types of key information on the doctor's homepage in the online medical community, collects eye movement data in real scenarios using eye tracking technology, processes the eye movement data and defines and calculates the corresponding indicators to obtain the attention index, thereby evaluating the importance of the above information. The application of eye tracking technology in the field of online medical communities is expanded, and the problem of relying on subjective feedback in traditional evaluation methods and the difficulty in accurately capturing users' real information attention is solved.

[0004] In order to achieve the above object, the present application adopts the following technical solutions: The present application provides an online medical community multi-information importance evaluation method based on eye movement technology, comprising the following steps: The multi-information in the online medical community is divided into doctor-generated information, patient-generated information and platform-generated information; The interest areas of the doctor homepage in the online medical community are divided based on the doctor-generated information, patient-generated information and platform-generated information; Eye movement data of each interest area is obtained based on an eye movement device; The eye movement data of each interest area is preprocessed; The total fixation duration, average fixation duration and unit average fixation duration of each interest area are calculated; The total fixation point number, average fixation point number and unit average fixation point number of each interest area are calculated; The attention degree is calculated based on the unit average fixation duration and unit average fixation point number; The online medical community multi-information importance evaluation result is obtained based on the attention degrees of different information areas.

[0005] As a preferred technical solution, the doctor-generated information includes doctor basic information, doctor profile, popular science article and doctor photo, the patient-generated information includes post-diagnosis evaluation and virtual gift, and the platform-generated information includes recommendation popularity and third-party authentication; The interest areas of the doctor homepage in the online medical community include doctor basic information area, doctor profile area, popular science special area, doctor photo area, post-diagnosis evaluation area, virtual gift area, recommendation popularity area and third-party authentication area.

[0006] As a preferred technical solution, the total fixation duration, average fixation duration and unit average fixation duration of each interest area are calculated, specifically including: The total fixation duration of each interest area is expressed as: ; Wherein, is the total fixation duration of the i-th interest area, is the fixation duration of the k-th user in the i-th interest area; The average fixation duration of each interest area is expressed as: ; Wherein, K is the total number of users, is the average fixation duration of the i-th interest area, reflecting the average input time of a single user in the interest area; The unit average fixation duration of each interest area is specifically expressed as: ; Wherein, is the area of the i-th interest area, is the unit average gaze duration of the i-th interest area.

[0007] As a preferred technical solution, the total number of gaze points, the average number of gaze points and the unit average number of gaze points of each interest area are calculated, which specifically includes: The total number of gaze points of each interest area is represented as: ; Wherein, is the total number of gaze points of the i-th interest area, is the number of gaze points of the k-th user in the i-th interest area; The average number of gaze points of each interest area is represented as: ; Wherein, K is the total number of users, is the average number of gaze points of the i-th interest area; The unit average number of gaze points of each interest area is represented as: ; Wherein, is the area of the i-th interest area, is the unit average number of gaze points of the i-th interest area.

[0008] As a preferred technical solution, the attention degree is calculated based on the unit average gaze duration and the unit average number of gaze points, which is specifically represented as: ; Wherein, represents the attention degree of the i-th interest area, is the unit average gaze duration of the i-th interest area, is the unit average number of gaze points of the i-th interest area.

[0009] The application also provides an online medical community multi-information importance evaluation system based on eye movement technology, which comprises: a multi-information division module, an interest area division module, an eye movement data acquisition module, a data preprocessing module, a gaze duration parameter calculation module, a gaze point parameter calculation module, an attention degree calculation module, and an evaluation result output module. The multi-information division module is used to divide the multi-information in the online medical community into doctor-generated information, patient-generated information and platform-generated information. The interest area division module is used to divide the interest area of the online medical community doctor homepage based on the doctor-generated information, the patient-generated information and the platform-generated information. The eye movement data acquisition module is configured to acquire eye movement data of each interest area based on an eye movement device; The data preprocessing module is configured to perform data preprocessing on the eye movement data of each interest area; The gaze duration parameter calculation module is configured to calculate total gaze duration, average gaze duration, and unit average gaze duration of each interest area; The gaze point parameter calculation module is configured to calculate total gaze points, average gaze points, and unit average gaze points of each interest area; The attention degree calculation module is configured to calculate the attention degree based on the unit average gaze duration and the unit average gaze points; The evaluation result output module is configured to obtain the multi-information importance evaluation result of the online medical community based on the attention degrees of different information areas.

[0010] As a preferred technical solution, the doctor-generated information includes doctor basic information, doctor profile, popular science articles, and doctor photos, the patient-generated information includes post-diagnosis evaluation and virtual gifts, and the platform-generated information includes recommendation popularity and third-party authentication; The interest areas of the online medical community doctor homepage include: doctor basic information area, doctor profile area, popular science area, doctor photo area, post-diagnosis evaluation area, virtual gift area, recommendation popularity area, and third-party authentication area.

[0011] As a preferred technical solution, the gaze duration parameter calculation module is configured to calculate total gaze duration, average gaze duration, and unit average gaze duration of each interest area, specifically including: The total gaze duration of each interest area is represented as: ; Wherein, is the total gaze duration of the i-th interest area, is the gaze duration of the k-th user in the i-th interest area; The average gaze duration of each interest area is represented as: ; Wherein, K is the total number of users, is the average gaze duration of the i-th interest area, reflecting the average input time of a single user in the interest area; The unit average gaze duration of each interest area is specifically represented as: ; Wherein, is the area of the i-th interest area, is the unit average gaze duration of the i-th interest area.

[0012] As a preferred technical scheme, the gaze point parameter calculation module is used for calculating the total gaze point number, the average gaze point number and the unit average gaze point number of each interest area, and specifically comprises the following steps: The total gaze point number of each interest area is expressed as: ; Wherein, is the total gaze point number of the i-th interest area, is the gaze point number of the k-th user in the i-th interest area; The average gaze point number of each interest area is expressed as: ; Wherein, K is the total number of users, is the average gaze point number of the i-th interest area; The unit average gaze point number of each interest area is expressed as: ; Wherein, is the area of the i-th interest area, is the unit average gaze point number of the i-th interest area.

[0013] As a preferred technical scheme, the attention degree calculation module is used for calculating the attention degree based on the unit average gaze duration and the unit average gaze point number, and the attention degree is specifically expressed as: ; Wherein, represents the attention degree of the i-th interest area, is the unit average gaze duration of the i-th interest area, is the unit average gaze point number of the i-th interest area.

[0014] Compared with the prior art, the present application has the following advantages and beneficial effects: According to the information characteristics in the online medical community, the present application divides the information into doctor-generated information, patient-generated information and platform-generated information, collects eye movement indicators based on eye movement technology, evaluates the importance of various types of information, identifies the key information affecting user selection of doctors, discovers the information in the interface that users pay more attention to, and can provide reference for platform information content optimization display, interface layout adjustment, user decision efficiency improvement, etc., expand the application of eye movement technology in the field of online medical community, and solve the problem that the traditional evaluation method relies on subjective feedback and is difficult to accurately capture the real information attention tendency of users. BRIEF DESCRIPTION OF DRAWINGS

[0015] Figure 1 is the flowchart of the online medical community multi-information importance evaluation method based on eye movement technology of the present application. DETAILED DESCRIPTION

[0016] In order to make the objectives, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and should not be used to limit the present application.

[0017] Embodiment 1 As shown in the embodiment, the embodiment provides an online medical community multi-information importance evaluation method based on eye movement technology, specifically comprising the following steps: Figure 1 S1: online medical community information division and interest area division, specifically comprising: dividing the multi-information in the online medical community into doctor-generated information, patient-generated information and platform-generated information, dividing the interest areas of the doctor homepage of the online medical community based on the doctor-generated information, patient-generated information and platform-generated information, each interest area representing a kind of information; Specifically, the doctor-generated information includes doctor basic information (title, hospital), doctor profile, popular science article, doctor photo, the patient-generated information includes post-diagnosis evaluation, virtual gift, and the platform-generated information includes recommendation popularity, third-party authentication, therefore, it can be divided into doctor basic information area, doctor profile area, popular science area, doctor photo area, post-diagnosis evaluation area, virtual gift area, recommendation popularity area, third-party authentication area, etc., the user can clearly and intuitively see the display of the three types of information in the online medical community, and they all have the possibility of being effective signals to attract users to select doctors, the embodiment focuses on the three types of key information of the doctor homepage of the online medical community, and collects eye movement data in a real scene by combining the eye movement tracking technology, processes the eye movement data and calculates corresponding indexes; S2: obtaining eye movement data of each interest area based on an eye movement device; In the embodiment, referring to the pages of the online medical community website in reality, a doctor homepage interface is made to ensure the readability of each page; meanwhile, in order to avoid the interference of the background on the eye movement behavior of the user, the background color is uniformly set to white to avoid the interference of the background elements on the eye movement behavior of the user; S3: defining indexes based on the eye movement data; In the present embodiment, the eye movement device is preferably a screen-based eye tracker, such as the Tobii Pro X3-120, with a sampling rate of 150 Hz. Compared with head-mounted eye movement devices, it has the advantages of easy operation, being conducive to collecting natural behavior, and being compatible with a wider range of user groups. The eye tracker operates on the principle of optical tracking. The instrument is equipped with a precise infrared emission and receiving device. When in operation, infrared light is emitted towards the user's eyes, and the eye structure reflects the infrared light. The reflected light is captured by a high-resolution camera. Since the cornea and pupil have different reflection characteristics for infrared light, by analyzing the angle, intensity and imaging position of the reflected light, the gaze point coordinates of the user's eyes can be accurately calculated, so that the key eye movement data such as the eye movement trajectory, gaze duration and saccade of the user can be obtained in real time and accurately.

[0018] S3: data preprocessing of the eye movement data of each interest area; In the present embodiment, abnormal, missing and repeated eye movement data are removed to obtain preprocessed eye movement data. S4: data index calculation and analysis, specifically including: S41: calculation of the total gaze duration, average gaze duration and unit average gaze duration of each interest area; The total gaze duration of each interest area is expressed as: ; wherein, is the total gaze duration of the i-th interest area, is the gaze duration of the k-th user in the i-th interest area.

[0019] The average gaze duration of each interest area is expressed as: ; wherein, K is the total number of users, is the average gaze duration of the i-th interest area, reflecting the average time input by a single user in the interest area; Because the areas occupied by each region are not the same, in order to exclude the influence of the occupied area on the analysis results and achieve more accurate analysis, the present embodiment calculates the unit average gaze duration of each interest area, which is specifically expressed as: ; wherein, is the area of the i-th interest area, is the unit average gaze duration of the i-th interest area, which is obtained by dividing the average gaze duration by the area of the interest area; S42: calculation of the total number of gaze points, average number of gaze points and unit average number of gaze points of each interest area; The total number of gaze points of each interest area is expressed as: ; wherein, is the total number of fixation points of the i-th interest area, is the number of fixation points of the k-th user in the i-th interest area.

[0020] The average number of fixation points of each interest area is expressed as: ; wherein, K is the total number of users, is the average number of fixation points of the i-th interest area.

[0021] Because the size of each area is not the same, in order to exclude the influence of the occupied area on the analysis result, and realize more accurate analysis, the embodiment calculates the unit average fixation point number of each interest area, which is specifically expressed as: ; wherein, is the area of the i-th interest area, is the unit average fixation point number of the i-th interest area, which is obtained by dividing the average fixation point number by the area of the interest area.

[0022] S43: Calculate the attention degree: ; wherein, indicates the attention degree of the i-th interest area, and the attention degree is obtained by dividing the unit average fixation time by the unit average fixation point number, which is used to measure the attention allocated by the user to the corresponding area during browsing, and reflects the attraction degree of the area to the user; S5: Evaluation result output: based on the attention degree of the user to different information areas, the evaluation result of the importance of multi-information in the online medical community is obtained.

[0023] Embodiment 2 The embodiment provides an online medical community multi-information importance evaluation system based on eye movement technology, which is used to realize the online medical community multi-information importance evaluation method based on eye movement technology in the above embodiment 1. The system comprises a multi-information division module, an interest area division module, an eye movement data acquisition module, a data preprocessing module, a fixation time parameter calculation module, a fixation point parameter calculation module, an attention degree calculation module, and an evaluation result output module. In the embodiment, the multi-information division module is used to divide the multi-information in the online medical community into doctor-generated information, patient-generated information and platform-generated information. Specifically, the doctor-generated information includes doctor basic information, doctor profile, popular science articles, and doctor photos, the patient-generated information includes post-diagnosis evaluation and virtual gifts, and the platform-generated information includes recommendation popularity and third-party authentication. The interest areas of the doctor homepage of the online medical community include: a doctor basic information area, a doctor profile area, a popular science area, a doctor photo area, a post-diagnosis evaluation area, a virtual gift area, a recommendation popularity area, and a third-party authentication area. In this embodiment, the interest area division module is configured to divide the interest areas of the doctor homepage of the online medical community based on the doctor-generated information, the patient-generated information, and the platform-generated information. In this embodiment, the eye movement data acquisition module is configured to acquire eye movement data of each interest area based on an eye movement device. In this embodiment, the data preprocessing module is configured to perform data preprocessing on the eye movement data of each interest area. In this embodiment, the fixation duration parameter calculation module is configured to calculate the total fixation duration, the average fixation duration, and the unit average fixation duration of each interest area, specifically including: The total fixation duration of each interest area is represented as: ; wherein, is the total fixation duration of the i-th interest area, is the fixation duration of the k-th user in the i-th interest area; The average fixation duration of each interest area is represented as: ; wherein, K is the total number of users, is the average fixation duration of the i-th interest area, reflecting the average input time of a single user in the interest area; The unit average fixation duration of each interest area is specifically represented as: ; wherein, is the area of the i-th interest area, is the unit average fixation duration of the i-th interest area.

[0024] In this embodiment, the fixation point parameter calculation module is configured to calculate the total number of fixation points, the average number of fixation points, and the unit average number of fixation points of each interest area, specifically including: The total number of fixation points of each interest area is represented as: ; wherein, is the total number of fixation points of the i-th interest area, is the number of fixation points of the k-th user in the i-th interest area; The average number of fixation points of each interest area is expressed as: ; Wherein, K is the total number of users, is the average number of fixation points of the i th interest area; The unit average number of fixation points of each interest area is expressed as: ; Wherein, is the area of the i th interest area, is the unit average number of fixation points of the i th interest area.

[0025] In the embodiment, the attention degree calculation module is used to calculate the attention degree based on the unit average fixation time and the unit average number of fixation points, and the attention degree is specifically expressed as: ; Wherein, represents the attention degree of the i th interest area, is the unit average fixation time of the i th interest area, is the unit average number of fixation points of the i th interest area.

[0026] In the embodiment, the evaluation result output module is used to obtain the multi-element information importance evaluation result of the online medical community based on the attention degrees of different information areas.

[0027] The above embodiment is the preferred embodiment of the present application, but the embodiment of the present application is not limited by the above embodiment, and any change, modification, substitution, combination, simplification made without departing from the spirit and principle of the present application should be equivalent replacement method, and all are included in the protection scope of the present application.

Claims

1. An online medical community multi-information importance evaluation method based on eye movement technology, characterized in that, The method comprises the following steps: dividing the multi-information in the online medical community into doctor-generated information, patient-generated information and platform-generated information; dividing the interest area of the doctor homepage of the online medical community based on the doctor-generated information, patient-generated information and platform-generated information; obtaining eye movement data of each interest area based on an eye movement device; performing data preprocessing on the eye movement data of each interest area; calculating the total fixation time, average fixation time and unit average fixation time of each interest area; calculating the total fixation point number, average fixation point number and unit average fixation point number of each interest area; calculating the attention degree based on the unit average fixation time and the unit average fixation point number; obtaining the importance evaluation result of the multi-information in the online medical community based on the attention degrees of different information areas. 2.The online medical community multi-information importance evaluation method based on eye movement technology according to claim 1, wherein, The doctor-generated information includes doctor basic information, doctor profile, popular science articles and doctor photos, the patient-generated information includes post-diagnosis evaluation and virtual gifts, and the platform-generated information includes recommendation popularity and third-party authentication. The interest area of the doctor homepage of the online medical community includes the doctor basic information area, the doctor profile area, the popular science area, the doctor photo area, the post-diagnosis evaluation area, the virtual gift area, the recommendation popularity area and the third-party authentication area. 3.The method of claim 1, wherein, The total fixation time, average fixation time and unit average fixation time of each interest area are calculated, specifically including: The total fixation time of each interest area is represented as: ； wherein, is the total gaze duration of the i-th region of interest, is the gaze duration of the k-th user in the i-th region of interest; The average fixation time of each interest area is represented as: ； wherein K is the total number of users, is the average gaze duration of the i-th interest area, reflecting the average time of a single user in the interest area. The unit average fixation time of each interest area is specifically represented as: ； wherein, is the area of the i-th region of interest, is the unit average fixation duration of the i-th region of interest. 4.The method of claim 1, wherein, The total fixation point number, average fixation point number and unit average fixation point number of each interest area are calculated, specifically including: The total fixation point number of each interest area is represented as: ； wherein, is the total number of gaze points of the i-th region of interest, is the number of gaze points of the k-th user in the i-th region of interest; The average fixation point number of each interest area is represented as: ； wherein K is the total number of users, is the average number of fixation points of the i-th interest zone. The unit average fixation point number of each interest area is represented as: ； wherein, is the area of the i-th region of interest, is the number of unit average fixation points of the i-th region of interest. 5.The method of claim 1, wherein, The attention degree is calculated based on the unit average fixation time and the unit average fixation point number, and is specifically represented as: ； wherein, represents the attention degree of the i-th region of interest, is the unit average fixation duration of the i-th region of interest, is the unit average fixation point number of the i-th region of interest.

6. An online medical community multi-information importance evaluation system based on eye movement technology, characterized in that, It comprises: a multi-information division module, an interest area division module, an eye movement data acquisition module, a data preprocessing module, a fixation time parameter calculation module, a fixation point parameter calculation module, an attention degree calculation module and an evaluation result output module; The multi-information division module is used to divide the multi-information in the online medical community into doctor-generated information, patient-generated information and platform-generated information; The interest area division module is used to divide the interest area of the doctor homepage of the online medical community based on the doctor-generated information, patient-generated information and platform-generated information; The eye movement data acquisition module is used to obtain eye movement data of each interest area based on an eye movement device; The data preprocessing module is used to perform data preprocessing on the eye movement data of each interest area; The fixation time parameter calculation module is used to calculate the total fixation time, average fixation time and unit average fixation time of each interest area; The fixation point parameter calculation module is used to calculate the total fixation point number, average fixation point number and unit average fixation point number of each interest area; The attention degree calculation module is used to calculate the attention degree based on the unit average fixation time and the unit average fixation point number; The evaluation result output module is used to obtain the importance evaluation result of the multi-information in the online medical community based on the attention degrees of different information areas.

7. The online medical community multi-information importance evaluation system based on eye movement technology according to claim 6, characterized in that, The doctor-generated information includes doctor basic information, doctor profile, popular science articles, and doctor photos, the patient-generated information includes post-diagnosis evaluation and virtual gifts, and the platform-generated information includes recommendation popularity and third-party authentication; The interest area of the doctor homepage of the online medical community includes: a doctor basic information area, a doctor profile area, a popular science area, a doctor photo area, a post-diagnosis evaluation area, a virtual gift area, a recommendation popularity area, and a third-party authentication area. 8.The online medical community multi-information importance evaluation system based on eye movement technology of claim 6, wherein, The gaze duration parameter calculation module is configured to calculate the total gaze duration, the average gaze duration, and the unit average gaze duration of each interest area, and specifically includes: The total gaze duration of each interest area is represented as: ； wherein, is the total gaze duration of the i-th region of interest, is the gaze duration of the k-th user in the i-th region of interest; The average gaze duration of each interest area is represented as: ； wherein K is the total number of users, is the average gaze duration of the i-th interest area, reflecting the average time of a single user in the interest area. The unit average gaze duration of each interest area is specifically represented as: ； wherein, is the area of the i-th region of interest, is the unit average fixation duration of the i-th region of interest. 9.The online medical community multi-information importance evaluation system based on eye movement technology of claim 6, wherein, The gaze point parameter calculation module is configured to calculate the total gaze point number, the average gaze point number, and the unit average gaze point number of each interest area, and specifically includes: The total gaze point number of each interest area is represented as: ； wherein, is the total number of gaze points of the i-th region of interest, is the number of gaze points of the k-th user in the i-th region of interest; The average gaze point number of each interest area is represented as: ； wherein K is the total number of users, is the average number of fixation points of the i-th interest zone. The unit average gaze point number of each interest area is represented as: ； wherein, is the area of the i-th region of interest, is the number of unit average fixation points of the i-th region of interest. 10.The online medical community multi-information importance evaluation system based on eye movement technology of claim 6, wherein, The attention degree calculation module is configured to calculate the attention degree based on the unit average gaze duration and the unit average gaze point number, and the attention degree is specifically represented as: ； wherein, represents the attention of the i-th region of interest, is the unit average fixation duration of the i-th region of interest, is the unit average fixation point number of the i-th region of interest.

Images