Medical content recommendation method, program product, device, equipment and storage medium

Abstract

The present disclosure provides a method, program product, apparatus, device, storage medium for recommending medical content, comprising: obtaining a first medical content set comprising at least one medical content describing a medical viewpoint, the at least one medical content having a content information density score and a description depth classification; historical data of the user is obtained, wherein the historical data comprises the understanding degree grade of the user on the corresponding medical viewpoint; determining a grading score of the at least one medical content based on the understanding degree grading and the description depth grading; determining an associated interactive behavior score of the user for the at least one medical content; determining a first weight of the grading score and a second weight of the associated interactive behavior score based on the information density score; obtaining a ranking score for the at least one medical content; and presenting the at least one medical content to the user.

Description

Technical Field

[0001] This invention relates to recommendation algorithms, and more particularly to methods, program products, apparatus, devices, and storage media for recommending medical content. Background Technology

[0002] Existing medical content recommendation algorithms typically rely on two main types of foundational data: the first is basic user behavior data, such as whether a user has already read certain content; the second is basic content tags, such as the content's domain (e.g., different disease areas, different departments), type (e.g., academic conference invitations, paper content), and upload date. Supported by this data, widely used medical content recommendation technologies primarily include collaborative filtering and content-based filtering. Collaborative filtering recommends content favored by similar users by mining group behavior patterns in user-item interaction records; content-based filtering, on the other hand, recommends content similar to the user's historical interests based on the item's own attribute characteristics.

[0003] However, while these methods have achieved significant results in scenarios such as e-commerce, news, and short videos, they have obvious shortcomings when applied to academic education. On the one hand, existing recommendation mechanisms lack a holistic understanding of users' academic growth paths and cannot dynamically adjust according to users' learning goals at different stages. Current recommendation logic still prioritizes "more clicks" and "longer dwell time" rather than being guided by knowledge acquisition and cognitive expansion. On the other hand, these algorithms easily exacerbate the "information cocoon" effect, where users are constantly bombarded with familiar or preferred content, leading to a limited perspective and difficulty accessing cross-disciplinary or challenging new materials, which is particularly detrimental to academic innovation and systematic knowledge construction.

[0004] Furthermore, existing methods generally ignore the differences in users' levels of academic knowledge. For beginners, directly recommending highly difficult papers may be counterproductive; while for advanced users, repeatedly recommending basic content will waste cognitive resources. This lack of hierarchical and progressive recommendation not only reduces learning efficiency but also fails to support users' long-term academic development.

[0005] Therefore, the goal is to achieve the objective of cultivating users' academic knowledge by ensuring that medical recommendations are attractive while promoting users' understanding and learning of medical perspectives. Summary of the Invention

[0006] This disclosure provides a method for recommending medical content, comprising: obtaining a first set of medical content, the first set of medical content including at least one piece of medical content describing a medical viewpoint, the at least one piece of medical content having a content information density score and a description depth rating of the medical viewpoint, wherein the information density score indicates the richness of the at least one piece of medical content; obtaining historical data of a user, the historical data including a rating of the user's level of understanding of the corresponding medical viewpoint; determining a rating score for the at least one piece of medical content based on the user's level of understanding of the medical viewpoint described by the at least one piece of medical content and the description depth rating of the medical viewpoint by the at least one piece of medical content; and determining... Based on at least one attribute parameter of the at least one medical content and the historical data, a score for the user's associated interaction behavior with the at least one medical content is determined, wherein the historical data also includes the user's previous associated interaction behavior with the at least one attribute parameter; a first weight for the grading score and a second weight for the associated interaction behavior score are determined based on the information density score; a ranking score for the at least one medical content is obtained based on the grading score, the first weight, the associated interaction behavior score, and the second weight; and the at least one medical content is presented to the user in descending order of the ranking scores of the at least one medical content.

[0007] According to an embodiment of the method of this disclosure, determining the rating score of the at least one medical content includes: determining the difference between the user's level of understanding of the medical viewpoint described by the at least one medical content and the level of the depth of description of the medical viewpoint by the at least one medical content; and configuring the rating score of the at least one medical content based on the difference.

[0008] According to an embodiment of the present disclosure, the method of determining the grading score of the at least one medical content includes: determining whether the difference is within a predetermined difference range; configuring a first grading score for the at least one medical content in response to the difference being within the predetermined difference range; and configuring a second grading score for the at least one medical content in response to the difference not being within the predetermined difference range, wherein the second grading score is lower than the first grading score.

[0009] According to the method of an embodiment of this disclosure, configuring a first grade score for the at least one medical content includes: adjusting the first grade score based on the user's level of understanding of the medical viewpoints described in the at least one medical content.

[0010] The method according to embodiments of the present disclosure further includes: describing multiple medical viewpoints in response to one of the at least one medical content; determining multiple graded scores for the one medical content for each of the multiple medical viewpoints; and determining the average of the multiple graded scores as the graded score of the one medical content.

[0011] According to an embodiment of the method of this disclosure, the level of understanding is obtained through an interactive control set in medical content previously read by the user, and wherein the interactive control is configured to: present one or more interactive contents related to a medical viewpoint to the user in response to the user selecting the interactive control, and determine the level of understanding of the medical viewpoint by the user based on the user's interaction with the one or more interactive contents.

[0012] According to an embodiment of the present disclosure, the interactive control is configured to: in response to a user obtaining multiple levels of understanding of a first medical viewpoint by selecting multiple interactive controls for a first medical viewpoint among multiple medical viewpoints, determine the average of the multiple levels of understanding as the user's level of understanding of the first medical viewpoint.

[0013] According to an embodiment of the present disclosure, presenting the at least one medical content to the user in descending order of the ranking scores of the at least one medical content comprises: in response to the at least one medical content having the same ranking score, presenting the at least one medical content to the user in descending order of the number of reads of the at least one medical content.

[0014] According to the method of embodiments of this disclosure, the at least one attribute parameter includes one or more of the drug name and the drug brand.

[0015] According to an embodiment of the present disclosure, obtaining a ranking score for the at least one medical content includes: multiplying the grading score by the first weight, multiplying the associated interaction behavior score by the second weight, and adding the information density score to obtain a ranking score for the at least one medical content.

[0016] According to an embodiment of the method of this disclosure, wherein the associated interaction behavior includes direct behavior, the method further includes: in response to determining from the historical data that the user has direct behavior toward the at least one attribute parameter, directly adjusting the associated interaction behavior score of the medical content corresponding to the at least one attribute parameter.

[0017] According to an embodiment of the method of this disclosure, wherein the associated interactive behavior includes indirect behavior, the method further includes: in response to determining, through the historical data, that the user has indirect behavior toward the at least one attribute parameter, determining the degree of interaction of the indirect behavior, and adjusting the associated interactive behavior score of the medical content corresponding to the at least one attribute parameter based on the degree of interaction of the indirect behavior.

[0018] According to the method of embodiments of this disclosure, determining the user's associated interaction behavior score for the at least one medical content includes: determining the time interval between the occurrence time of the associated interaction behavior and the current time based on the historical data, and attenuating the associated interaction behavior score based on the time interval.

[0019] According to an embodiment of the present disclosure, the method further includes: obtaining a second medical content set, the second medical content set including at least one medical content that the user has not read, and placing the second medical content set after the first medical content set for presentation to the user.

[0020] According to an embodiment of the present disclosure, the method further includes: determining the publication time of at least one piece of medical content that the user has read, and presenting the at least one piece of medical content that the user has read to the user in reverse chronological order of the publication time.

[0021] According to the method of an embodiment of this disclosure, the magnitude of the information density score is positively correlated with the magnitude of the first weight.

[0022] According to the method of an embodiment of this disclosure, the magnitude of the information density score is negatively correlated with the magnitude of the second weight.

[0023] Embodiments of this disclosure provide an apparatus for recommending medical content, comprising: a medical content module configured to obtain a first set of medical content, the first set of medical content including at least one piece of medical content describing a medical viewpoint, the at least one piece of medical content having a description depth rating of the medical viewpoint; a historical data module configured to obtain historical data of a user, the historical data including a rating of the user's level of understanding of the corresponding medical viewpoint; a rating score module configured to determine a rating score for the at least one piece of medical content based on the user's level of understanding of the medical viewpoint described by the at least one piece of medical content and the description depth rating of the medical viewpoint by the at least one piece of medical content; and a content presentation module configured to sort the at least one piece of medical content at least in part based on the rating score for presentation to the user.

[0024] Embodiments of this disclosure provide an apparatus for recommending medical content, comprising: one or more processors; and one or more memories storing a computer-executable program that, when executed by the processor, performs the method described above.

[0025] Embodiments of this disclosure provide a computer program product, including a computer program or instructions, wherein the computer program or instructions, when executed by a processor, implement the method described above.

[0026] Embodiments of this disclosure provide a computer-readable storage medium having computer-executable instructions stored thereon, which, when executed by a processor, are used to implement the method described above.

[0027] The method for recommending medical content disclosed herein can promote users' understanding and learning of medical perspectives while ensuring the recommended content is attractive, thereby achieving the goal of academic education for users. For example, the method not only considers users' immediate browsing preferences but also takes into account academic learning objectives, thus recommending medical content that describes insightful medical perspectives suitable for users' current cognitive level. Therefore, this method can maintain user engagement while effectively promoting their understanding and long-term accumulation of complex medical content, thereby achieving a leap from "recommending information" to "cultivating academic ability." Attached Figure Description

[0028] The above and other aspects, features, and advantages of specific embodiments of the present disclosure will become clearer from the following description taken in conjunction with the accompanying drawings, in which:

[0029] Figure 1 This is a schematic diagram of the flow of a method for recommending medical content according to embodiments of the present disclosure.

[0030] Figure 2 This is a schematic diagram of the flow of a method for recommending medical content according to embodiments of the present disclosure.

[0031] Figure 3 An apparatus for recommending medical content according to an embodiment of the present disclosure is shown.

[0032] Figure 4 A schematic diagram of a device 400 for recommending medical content according to an embodiment of the present disclosure is shown.

[0033] Figure 5 A computing device for recommending medical content is shown according to an embodiment of the present disclosure. Detailed Implementation

[0034] Before proceeding with the detailed description below, it may be advantageous to define certain words and phrases used throughout this disclosure. The terms “comprising” and “including” and their derivatives mean, but are not limited to, “including”. The phrase “at least one”, when used with a list of items, means that different combinations of one or more of the listed items may be used, and that only one item in the list may be required. For example, “at least one of A, B, and C” includes any one of the following combinations: A, B, C, A and B, A and C, B and C, A and B and C.

[0035] Definitions of other specific words and phrases are provided throughout this disclosure. Those skilled in the art will understand that, in many, if not most, cases, such definitions apply to the prior and future use of the words and phrases thus defined.

[0036] The various embodiments of the principles of this disclosure described below in conjunction with the accompanying drawings are for illustrative purposes only and should not be construed as limiting the scope of this disclosure in any way. Those skilled in the art will understand that the principles of this disclosure can be implemented in any suitably arranged system or device. In some cases, the actions described in this disclosure may be performed in a different order and still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require a specific order or sequential sequence to achieve the desired result. In certain embodiments, multitasking and parallel processing may be advantageous.

[0037] The text and accompanying drawings are provided by way of example only to aid in understanding this disclosure. They should not be construed as limiting the scope of the claims appended to this disclosure in any way. Throughout the drawings, the same reference numerals generally indicate the same elements. Although certain embodiments and examples have been provided, it will be apparent to those skilled in the art, based on the content of this disclosure, that changes may be made to the illustrated embodiments and examples without departing from the scope of this disclosure.

[0038] Figure 1 This is a schematic flowchart of a method for recommending medical content according to embodiments of this disclosure. Figure 1 As shown, method 1000 may include steps S1110-S1400.

[0039] In step S1100, a first medical content set can be obtained, which includes at least one medical content describing a medical viewpoint, and the at least one medical content has a content information density score and a description depth rating of the medical viewpoint.

[0040] In one embodiment, the first medical content set may include or may be a collection of medical content for displaying to a user. Users may include doctors from different departments or specialties. Medical viewpoints may include different brands. The first medical content set may include at least one piece of medical content describing a medical viewpoint. For example, the medical content included in the first medical content set may each describe one or more medical viewpoints. The depth rating of the description of the medical viewpoint may include multiple levels, such as a low level (e.g., level 1) describing introductory knowledge of the medical viewpoint and suitable for users unfamiliar with the medical viewpoint, an intermediate level (e.g., level 2) describing advanced knowledge of the medical viewpoint and suitable for users with some knowledge of the medical viewpoint, and a high level (e.g., level 3) describing complex knowledge of the medical viewpoint and suitable for users proficient in the medical viewpoint, etc., but this disclosure is not limited thereto, and the depth rating of the description of the medical viewpoint may include more or fewer levels.

[0041] Information density score can indicate the richness of at least one piece of medical content. The information density score can be a static attribute pre-calculated for at least one piece of medical content. Therefore, the information density score can represent the potential value of at least one piece of medical content. In one embodiment, the information density score can be determined based on the number of key messages associated with at least one piece of medical content included in the at least one piece of medical content. In one embodiment, in response to the number of associated key messages included in at least one piece of medical content being greater than or equal to a first number (e.g., greater than or equal to 4, but not limited thereto), the information density score of at least one piece of medical content can be determined as a high information density score (e.g., 3 points, but not limited thereto). In response to the number of associated key messages included in at least one piece of medical content being less than the first number and greater than a second number (e.g., less than 4, greater than 1, e.g., 2 or 3, but not limited thereto), the information density score of at least one piece of medical content can be determined as a medium information density score (e.g., 2 points, but not limited thereto). In response to the number of associated key messages included in at least one piece of medical content being less than or equal to a second number (e.g., less than or equal to 1, but not limited thereto), the information density score of at least one piece of medical content can be determined as a low information density score (e.g., 1 point, but not limited thereto). In step S1200, the user's historical data can be obtained, which includes a rating of the user's level of understanding of the relevant medical viewpoints.

[0042] In one embodiment, historical data may be data previously entered by the user. For example, historical data may be obtained based on information entered by the user when performing a registration operation; historical data may be obtained based on input by the user when performing a questionnaire, but this disclosure is not limited to these, and other ways of obtaining historical data are also possible. The user's level of understanding of the medical viewpoint may include multiple levels, for example, a low level indicating no understanding of the medical viewpoint (e.g., level 1-2), a medium level indicating some understanding of the medical viewpoint (e.g., level 3), a high level indicating proficiency in the medical viewpoint (e.g., level 4-5), etc., but this disclosure is not limited to these, and the level of understanding of the medical viewpoint may include more or fewer levels.

[0043] In step S1300, the rating score of at least one medical content can be determined based on the user's level of understanding of the medical viewpoints described in at least one medical content and the level of the depth of description of the medical viewpoints by at least one medical content.

[0044] In one embodiment, a rating score for at least one piece of medical content can be determined based on the match between a user's level of understanding of the medical viewpoints described in at least one piece of medical content and the depth of the medical viewpoints described in at least one piece of medical content. For example, the difference between a user's level of understanding of the medical viewpoints described in at least one piece of medical content and a depth of description of the medical viewpoints described in at least one piece of medical content can be determined. In one embodiment, the difference can be obtained by subtracting the user's level of understanding of the medical viewpoints described in at least one piece of medical content from the depth of description of the medical viewpoints described in at least one piece of medical content. Based on this difference, a rating score for at least one piece of medical content can be configured.

[0045] In step S1400, at least one attribute parameter of at least one piece of medical content can be determined. Based on the at least one attribute parameter and historical data, a user's associated interaction behavior score for the at least one piece of medical content is determined, wherein the historical data also includes the user's previous associated interaction behavior with the at least one attribute parameter. For example, associated interaction behavior includes at least one of direct and indirect behaviors. The user's associated interaction behavior score for the at least one piece of medical content can be determined based on at least one attribute parameter of the at least one piece of medical content and the user's previous associated interaction behavior with the at least one attribute parameter.

[0046] In step S1500, a first weight for the grading score and a second weight for the associated interactive behavior score can be determined based on the information density score. According to embodiments of this disclosure, the information density score can be correlated with both the grading score and the associated interactive behavior score. The first weight applied to the grading score and the second weight applied to the associated interactive behavior score can be determined based on the information density score.

[0047] In step S1600, a ranking score for at least one piece of medical content can be obtained based on the hierarchical score, the first weight, the associated interaction behavior score, and the second weight. According to embodiments of this disclosure, the first weight can be applied to the hierarchical score, and the second weight can be applied to the associated interaction behavior score to obtain a ranking score for at least one piece of medical content.

[0048] In step S1700, at least one piece of medical content may be presented to the user in descending order of its ranking score.

[0049] In one embodiment, the medical content included in the first medical content set can each receive a different ranking score. At least one piece of medical content included in the first medical content set can be sorted in descending order, at least in part, based on the ranking score, and then presented to the user. In this way, while ensuring the recommended content is attractive, it can promote the user's understanding and learning of medical perspectives, thereby achieving the goal of academic education for the user.

[0050] Figure 2 This is a schematic flowchart of a method for recommending medical content according to embodiments of this disclosure. Figure 2 As shown, method 2000 may include steps S2110-S2600. Figure 2 Zhongyu Figure 1 The same or similar steps will not be described again to avoid redundancy.

[0051] In step S2200, the user's historical data can be obtained, which includes the user's level of understanding of the corresponding medical viewpoints.

[0052] In one embodiment, the level of understanding can be obtained through interactive controls embedded in medical content previously read by the user. For example, interactive controls for conducting a questionnaire can be embedded in the medical content. These interactive controls can be configured to present one or more interactive content items related to a medical viewpoint to the user in response to the user's selection of the interactive control. The one or more interactive content items can be in the form of a questionnaire. For example, the interactive controls can display one or more questions related to a medical viewpoint, and can also display one or more answers to those questions for the user to select. Alternatively, the interactive controls can display one or more questions related to a medical viewpoint, and can also display one or more answer areas for the questions for the user to enter their answers. Based on the user's interaction with one or more interactive content items, the user's level of understanding of the medical viewpoint can be determined. For example, by analyzing the user's answers to one or more questions related to a medical viewpoint, the user's level of understanding of the corresponding medical viewpoint can be determined.

[0053] In one embodiment, in response to a user obtaining multiple levels of understanding of a first medical viewpoint by selecting multiple interactive controls for that first medical viewpoint among multiple medical viewpoints, the average of the multiple levels of understanding is determined as the user's level of understanding of the first medical viewpoint. For example, a user may answer a questionnaire multiple times for the same medical viewpoint and obtain multiple levels of understanding for that same medical viewpoint. The average of the multiple levels of understanding can be determined as the user's final level of understanding of that medical viewpoint.

[0054] In step S2300, the grading score of at least one medical content can be determined based on the user's level of understanding of the medical viewpoint described in at least one medical content and the grading of the depth of description of the medical viewpoint by at least one medical content.

[0055] In one embodiment, a rating score for at least one piece of medical content can be determined based on the match between a user's level of understanding of the medical viewpoints described in at least one piece of medical content and the depth of the medical viewpoints described in at least one piece of medical content. For example, the difference between a rating of the user's level of understanding of the medical viewpoints described in at least one piece of medical content and a rating of the depth of the medical viewpoints described in at least one piece of medical content can be determined.

[0056] In one embodiment, a difference can be obtained by subtracting the user's level of understanding of the medical viewpoint described by the at least one medical content from the description depth rating of the medical viewpoint described by the at least one medical content. It can be determined whether the difference is within a predetermined difference range. If the difference is within the predetermined difference range, a first rating score is assigned to the at least one medical content; if the difference is not within the predetermined difference range, a second rating score is assigned to the at least one medical content, wherein the second rating score is lower than the first rating score.

[0057] For example, the depth of description of a medical viewpoint can be graded into five levels, such as levels 1-5 representing the depth of description from shallow to deep; the user's level of understanding of a medical viewpoint can also be graded into five levels, such as levels 1-5 representing the level of understanding from shallow to deep. According to embodiments of this disclosure, if medical content describes a medical viewpoint that the user's level of understanding is low (e.g., level 1 or level 2), and the difference between the depth of the medical content's description of the medical viewpoint and the user's level of understanding is within a predetermined range (e.g., between 0 and 1), then the medical content receives a first-level score of 3 points for that medical viewpoint. For example, if medical content describes a medical viewpoint that the user's level of understanding is low (e.g., level 1 or level 2), and the difference between the depth of the medical content's description of the medical viewpoint and the user's level of understanding is not within a predetermined range (e.g., not between 0 and 1), then the medical content receives a second-level score of 0 points for that medical viewpoint. In other words, the method disclosed herein can recommend medical content to users with a description depth rating slightly higher than the user's level of understanding of the medical viewpoint, thereby promoting the user's mastery of the medical viewpoint and enhancing academic training objectives.

[0058] In one embodiment, the first-level score can be adjusted based on the user's level of understanding of the medical viewpoints described in at least one medical content description. That is, the difference between the user's level of understanding and the level of description depth of the medical content can be within a predetermined range for different medical viewpoints; however, because the user's level of understanding varies, the first-level score corresponding to different medical viewpoints can differ. For example, when the difference is within a predetermined range, the lower the user's level of understanding of the medical viewpoint, the higher the score they receive.

[0059] According to embodiments of this disclosure, if medical content describes a medical viewpoint that a user's level of understanding is low (e.g., level 1 or level 2), and the difference between the depth of the medical content's description of the medical viewpoint and the user's level of understanding of the medical viewpoint is within a predetermined range (e.g., between 0 and 1), then the medical content receives a first-level score of 3 points for that medical viewpoint. For example, if medical content describes a medical viewpoint that a user's level of understanding is low (e.g., level 1 or level 2), and the difference between the depth of the medical content's description of the medical viewpoint and the user's level of understanding of the medical viewpoint is not within a predetermined range (e.g., not between 0 and 1), then the medical content receives a second-level score of 0 points for that medical viewpoint. In this way, it is possible to prioritize influencing the perceptions of users with low levels of understanding, thereby achieving academic training objectives.

[0060] According to embodiments of this disclosure, if medical content describes a medical viewpoint that the user's level of understanding is classified as medium (e.g., level 3), and the difference between the depth of the medical content's description of the medical viewpoint and the user's level of understanding of the medical viewpoint is within a predetermined range (e.g., between 0 and 1), then the medical content receives a first-level score of 1 for that medical viewpoint. For example, if medical content describes a medical viewpoint that the user's level of understanding is classified as medium (e.g., level 3), and the difference between the depth of the medical content's description of the medical viewpoint and the user's level of understanding of the medical viewpoint is not within a predetermined range (e.g., not between 0 and 1), then the medical content receives a second-level score of 0 for that medical viewpoint. In this way, security exploration can be conducted to attempt to further influence and improve the perceptions of users with a medium level of understanding.

[0061] According to embodiments of this disclosure, if medical content describes a medical viewpoint that the user's level of understanding is rated as high (e.g., level 4 or level 5), and the difference between the depth of the medical content's description of the medical viewpoint and the user's level of understanding of the medical viewpoint is within a predetermined range (e.g., between 0 and 1), then the medical content receives a first-level score of 0.2 for that medical viewpoint. For example, if medical content describes a medical viewpoint that the user's level of understanding is rated as high (e.g., level 4 or level 5), and the difference between the depth of the medical content's description of the medical viewpoint and the user's level of understanding of the medical viewpoint is not within a predetermined range (e.g., not between 0 and 1), then the medical content receives a second-level score of 0 for that medical viewpoint. In this way, the understanding of users with a high level of understanding can be reinforced, and their perceptions maintained.

[0062] Using the above method, when medical content describes medical viewpoints that users are relatively unfamiliar with, and the depth of the description matches the user's understanding of those viewpoints, a higher rating can be assigned to that medical viewpoint, thereby promoting the user's academic training goals related to that viewpoint. Conversely, when medical content describes medical viewpoints that users are relatively familiar with, and the depth of the description matches the user's understanding of those viewpoints, a lower rating can be assigned to that medical viewpoint, thus providing an opportunity to recommend other medical content, including viewpoints that the user is relatively unfamiliar with, to the user.

[0063] According to embodiments of this disclosure, if medical content describes a medical viewpoint that the user's level of understanding is classified as unknown (e.g., the user's level of understanding of the medical viewpoint cannot be obtained based on historical data), then the medical content receives a first-level score of 0.5 for that medical viewpoint. In this way, unknown areas can be explored gently to identify the user's potential academic training goals.

[0064] In one embodiment, a single medical content item within at least one medical content item may describe multiple medical viewpoints. Therefore, for each of the multiple medical viewpoints, multiple graded scores can be assigned to each individual medical content item. The average of these multiple graded scores can be determined as the graded score for that single medical content item.

[0065] In step S2400, at least one attribute parameter of at least one piece of medical content can be determined. Based on the at least one attribute parameter and historical data, a score for the user's associated interaction behavior with the at least one piece of medical content is determined, wherein the historical data also includes the user's previous associated interaction behavior with the at least one attribute parameter. The at least one attribute parameter includes one or more of the following: drug name and drug brand. For example, the medical content may describe drugs with different names from different drug brands.

[0066] In one embodiment, historical data also includes a user's previous associated interactions with at least one attribute parameter. For example, associated interactions include at least one of direct and indirect behaviors.

[0067] For example, in response to the determination, based on historical data, that a user has engaged in direct behavior related to at least one attribute parameter, the score of the associated interactive behavior with the medical content corresponding to that attribute parameter can be directly adjusted. Direct behavior could include meetings the user has attended that described the drug name or brand in the medical content. In response to the user's direct behavior related to at least one attribute parameter, the score of the direct associated interactive behavior with the medical content corresponding to that attribute parameter can be directly set to 1 point. In this way, medical content that the user might be interested in can be recommended, thereby encouraging user reading.

[0068] For example, by determining from historical data that a user has engaged in indirect behavior related to at least one attribute parameter, the degree of interaction of this indirect behavior can be determined. Indirect behavior may include the user having previously saved, shared, and / or liked articles describing drug names or brands related to medical content, or having previously read in-depth articles describing drug names or brands related to medical content. In-depth reading may refer to reading behavior lasting longer than a predetermined time (e.g., 10 seconds, or longer or shorter, but this disclosure is not limited thereto). In one embodiment, the degree of interaction may include the number of articles describing drug names or brands related to medical content that the user has saved, shared, and / or liked. In another embodiment, the degree of interaction may include the number of articles describing drug names or brands related to medical content that the user has read in-depth.

[0069] For example, the score for related interactive behaviors of medical content corresponding to at least one attribute parameter can be adjusted based on the degree of interaction of indirect behaviors. For example, if a user has collected, shared, and / or liked 0 articles about drug names or brands describing medical content, they will receive a first related interactive behavior score of 0 for that medical content. For example, if a user has collected, shared, and / or liked 1 article about drug names or brands describing medical content, they will receive a first related interactive behavior score of 0.5 for that medical content. For example, if a user has collected, shared, and / or liked 2 or more articles about drug names or brands describing medical content, they will receive a first related interactive behavior score of 1 for that medical content. For example, if a user has read 0 articles about drug names or brands describing medical content in depth, they will receive a second related interactive behavior score of 0 for that medical content. For example, if a user has read 1 article about drug names or brands describing medical content in depth, they will receive a second related interactive behavior score of 0.5 for that medical content. For example, if a user reads at least two articles describing drug names and brands related to medical content, they will receive a second related interaction behavior score of 1 point for that medical content. The average of the first and second related interaction behavior scores can be determined as the indirect related interaction behavior score for that medical content.

[0070] In one embodiment, the time interval between the occurrence of a relevant interaction and the current time can be determined based on historical data, and the score of the relevant interaction can be decayed based on this time interval. For example, if the relevant interaction occurred within one week of the current time, the corresponding score will not decay. If the relevant interaction occurred within two weeks of the current time, the score will be multiplied by a 70% decay factor. If the relevant interaction occurred within three weeks of the current time, the score will be multiplied by a 40% decay factor. If the relevant interaction occurred more than three weeks ago, the score will be multiplied by a 20% decay factor. In this way, the timeliness of the recommended content can be enhanced.

[0071] In one embodiment, the product of the score of directly related interactive behavior and the attenuation coefficient and the product of the score of indirectly related interactive behavior and the attenuation coefficient can be summed to obtain the score of related interactive behavior of medical content.

[0072] In step S2500, a first weight for the grading score and a second weight for the associated interactive behavior score can be determined based on the information density score. The information density score allows at least one piece of medical content to be ranked according to its information content. According to embodiments of this disclosure, the magnitude of the information density score can be positively correlated with the magnitude of the first weight. Since medical content with a high information density score has more associated key information, a higher first weight can be assigned to it in order to ensure that the medical content is highly matched with the user's cognitive level and advanced goals. According to embodiments of this disclosure, the magnitude of the information density score can be negatively correlated with the magnitude of the second weight. Since medical content with a low information density score has less associated key information, a higher second weight can be assigned to it in order to attract users and maintain interaction. Specifically, the relationship between the information density score, the first weight, and the second weight can be referred to in the following table:

[0073]

[0074] In step S2600, the product of the grading score and the first weight, the product of the related interaction behavior score and the second weight, and the information density score can be added together to obtain a ranking score for at least one medical content. Specifically, the ranking score can be calculated using the following formula:

[0075] Ranking score = Information density score + (First weight * Tier score) + (Second weight * Related interaction behavior score)

[0076] In other words, according to embodiments of this disclosure, the information density score not only provides a basic score but also controls the weighting of the graded score and the score related to interactive behavior. That is, for complex medical content, more emphasis can be placed on academic training objectives; for simple medical content, more emphasis can be placed on user interests. Furthermore, the amount of key information can be obtained very easily, typically calculated directly from a medical content tagging system without any manual intervention.

[0077] At least one piece of medical content can be presented to the user in descending order of its ranking score. If at least one piece of medical content has the same ranking score, it can be presented to the user in descending order of its readership. This ensures that the recommendation results reflect both the user's level of understanding of medical viewpoints and the popularity of medical content.

[0078] Specifically, let's assume the user is Dr. Zhang, the head of the oncology department at a top-tier hospital, whose primary focus is on lung cancer. Dr. Zhang has the following historical data:

[0079] "Level 2 understanding of the medical perspective of 'Brand A's drug'"

[0080] The level of understanding of "Brand B's drug" at level 3 is graded according to medical perspectives;

[0081] The level of understanding of "Brand C drugs" at level 4 is graded according to medical perspectives;

[0082] I participated in Brand A's online meetings within 2 weeks (direct action);

[0083] I saved one article by Brand A within two weeks (indirect action);

[0084] I read two articles from Brand B in depth (>10 seconds) within two weeks (indirect behavior).

[0085] The first medical content set may include the following medical content:

[0086] Medical Content 1: "Drug X Phase III Clinical OS Data Update: Brand A" (Description depth is rated as Level 2, and information density score is 3)

[0087] Medical Content 2: "Real-world study on the safety of drug Y: Brand B" (Description depth is rated as level 4, and information density score is 3)

[0088] Medical Content 3: "Expert Consensus on Monotherapy with Drug Z: Brand C" (Description depth is graded as level 5, and information density score is 2)

[0089] Medical Content 4: "New Evidence that Drug W Improves Quality of Life: Brand D" (Description depth rating: Level 5, Information Density score: 1)

[0090] Calculation process:

[0091]

[0092] Therefore, based on the descending order of the ranking scores of at least one piece of medical content, at least one piece of medical content can be presented to the user in the following order:

[0093] "1. Medical content 1 (9.525 points)

[0094] 2. Medical content 2 (5.35 points)

[0095] 3. Medical content 3 (2.2 points)

[0096] 4. Medical content 4 (1.25 points)”.

[0097] The ranking results are highly consistent with the academic training objectives. Medical Content 1 and Medical Content 2, due to their high information density, received significantly weighted scores, occupying the top two positions. Although Medical Content 4 scored higher than Medical Content 3, its information density score of 1 reduced the primary weight of its ranking score, resulting in a lower overall score than Medical Content 3.

[0098] In one embodiment, the first medical content set includes at least one medical content that the user has not read. That is, the medical content in the first medical content set is content that the user has not read. According to the method of embodiments of this disclosure, a second medical content set can be obtained, the second medical content set including at least one medical content that the user has read. The second medical content set can be placed after the first medical content set for presentation to the user. That is, read content can be placed after unread content when presented to the user.

[0099] According to embodiments of this disclosure, the publication time of at least one piece of medical content that a user has read can be determined, and the at least one piece of medical content that the user has read can be presented to the user in reverse chronological order of publication time. That is, after setting read content after unread content, at least one piece of medical content that has been read can be presented to the user in chronological order of publication time of read content (e.g., the earlier the content was published, the earlier it appears in the order).

[0100] For example, suppose Dr. Zhang has already read:

[0101] • Medical Content 1: Advances in Lung Cancer Immunotherapy (Published 3 days ago)

[0102] •Medical Content 2: "New Drug Development for Cancer" (Published 5 days ago).

[0103] At least one medical content item that has been read can be presented to the user in chronological order of publication time (e.g., earlier published content appears first).

[0104] Medical Content 2: "New Drug Development for Cancer" (5 days ago)

[0105] Medical Content 1: Advances in Immunotherapy for Lung Cancer (3 days ago).

[0106] According to the method of embodiments of this disclosure, a third medical content set can be obtained, which includes at least one piece of medical content intended to be presented to a user. The third medical content set can be placed before a first medical content set for presentation to the user. That is, the third medical content set can be pinned to the top. For example, the third medical content set may include medical content such as the "2024 Lung Cancer Treatment Guidelines".

[0107] In this way, the following medical content can be presented to users:

[0108] === Third Medical Content Collection ===

[0109] 1. [Latest] 2024 Lung Cancer Treatment Guidelines (Pinned by Operations Team)

[0110] === First Medical Content Collection ===

[0111] 2. "Drug X Phase III Clinical Survival Data Update: Brand A"

[0112] 3. "Real-world safety study of drug Y: Brand B"

[0113] 4. "Expert Consensus on Drug Z Monotherapy: Brand C"

[0114] 5. "New Evidence that Drug W Improves Quality of Life: Brand D"

[0115] === Second Medical Content Collection ===

[0116] 6. Meeting replay: "New Drug Development for Oncology" (5 days ago)

[0117] 7. Article "Advances in Immunotherapy for Lung Cancer" (3 days ago).

[0118] The method for recommending medical content disclosed herein can promote users' understanding and learning of medical perspectives while ensuring the recommended content is attractive, thereby achieving the goal of academic education for users. For example, the method not only considers users' immediate browsing preferences but also takes into account academic learning objectives, thus recommending medical content that describes insightful medical perspectives suitable for users' current cognitive level. Therefore, this method can maintain user engagement while effectively promoting their understanding and long-term accumulation of complex medical content, thereby achieving a leap from "recommending information" to "cultivating academic ability."

[0119] The method disclosed herein establishes different differentiated scoring mechanisms based on users' varying levels of understanding of medical viewpoints, thereby prioritizing the exposure of medical content that matches their level of understanding, breaking through traditional strategies and promoting the achievement of content reach strategies.

[0120] Figure 3 An apparatus for recommending medical content according to embodiments of the present disclosure is shown. Figure 3 As shown, the device 3000 for recommending medical content may include a medical content module 3100, a historical data module 3200, a grading and scoring module 3300, an associated interactive behavior scoring module 3400, a weighting module 3500, a sorting module 3600, and a content presentation module 3700.

[0121] The medical content module 3100 can be configured to obtain a first medical content set, the first medical content set including at least one medical content describing a medical viewpoint, the at least one medical content having a content information density score and a description depth rating of the medical viewpoint, wherein the information density score indicates the richness of the at least one medical content.

[0122] The historical data module 3200 can be configured to obtain the user's historical data, which includes a grading of the user's understanding of the relevant medical viewpoints.

[0123] The grading and scoring module 3300 can be configured to determine the grading score of at least one piece of medical content based on the user's level of understanding of the medical viewpoint described in at least one piece of medical content and the depth of description of the medical viewpoint by at least one piece of medical content.

[0124] The related interaction behavior scoring module 3400 can be configured to determine at least one attribute parameter of at least one medical content, and based on at least one attribute parameter and historical data, determine a user's related interaction behavior score for at least one medical content, wherein the historical data also includes the user's previous related interaction behavior for at least one attribute parameter.

[0125] The weight module 3500 can be configured to determine the first weight of the graded score based on the information density score and the second weight of the associated interactive behavior score.

[0126] The ranking module 3600 can be configured to obtain a ranking score for at least one medical content based on the graded score, the first weight, the associated interactive behavior score, and the second weight.

[0127] The content presentation module 3700 can be configured to present at least one piece of medical content to the user in descending order of the sorting scores of at least one piece of medical content.

[0128] According to another aspect of this disclosure, a device for recommending medical content is also provided. Figure 4 A schematic diagram of a device 400 for recommending medical content according to an embodiment of the present disclosure is shown.

[0129] like Figure 4 As shown, the device 400 for recommending medical content may include one or more processors 410 and one or more memories 420. The memories 420 store computer-readable code that, when executed by the one or more processors 410, can perform the method for recommending medical content as described above.

[0130] The processor in the embodiments of this disclosure can be an integrated circuit chip with signal processing capabilities. The processor can be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), an off-the-shelf programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor can be a microprocessor or any conventional processor, and can be based on an x86 architecture or an ARM architecture.

[0131] In general, the various exemplary embodiments of this disclosure can be implemented in hardware or dedicated circuitry, software, firmware, logic, or any combination thereof. Some aspects can be implemented in hardware, while others can be implemented in firmware or software that can be executed by a controller, microprocessor, or other computing device. When aspects of embodiments of this disclosure are illustrated or described as block diagrams, flowcharts, or using some other graphical representation, it will be understood that the blocks, apparatuses, systems, techniques, or methods described herein can be implemented as non-limiting examples in hardware, software, firmware, dedicated circuitry or logic, general-purpose hardware or controllers or other computing devices, or some combination thereof.

[0132] For example, the method or apparatus according to embodiments of this disclosure can also be used by means of Figure 5The architecture of the computing device 500 shown is used for implementation. For example... Figure 5 As shown, the computing device 500 may include a bus 510, one or more CPUs 520, a read-only memory (ROM) 530, a random access memory (RAM) 540, a communication port 550 connected to a network, an input / output component 560, a hard disk 570, etc. The storage devices in the computing device 500, such as the ROM 570 or the hard disk 570, may store various data or files used for processing and / or communication of the methods for recommending medical content provided in this disclosure, as well as program instructions executed by the CPU. The computing device 500 may also include a user interface 580. Of course, Figure 5 The architecture shown is merely exemplary and can be omitted as needed when implementing different devices. Figure 5 One or more components in the computing device shown.

[0133] According to another aspect of this disclosure, a computer-readable storage medium is also provided. The computer storage medium stores computer-readable instructions. When the computer-readable instructions are executed by a processor, a method for recommending medical content according to embodiments of this disclosure, as described with reference to the above-drawn figures, can be performed. The computer-readable storage medium in the embodiments of this disclosure may be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. Non-volatile memory may be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. Volatile memory may be random access memory (RAM), which serves as an external cache. By way of example, but not limitation, many forms of RAM are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous linked dynamic random access memory (SLDRAM), and direct memory bus random access memory (DR RAM). It should be noted that the memory used in the methods described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0134] Embodiments of this disclosure also provide a computer program product or computer program including computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform a method for recommending medical content according to embodiments of this disclosure.

[0135] It should be noted that the flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing at least one executable instruction for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0136] In general, the various exemplary embodiments of this disclosure can be implemented in hardware or dedicated circuitry, software, firmware, logic, or any combination thereof. Some aspects can be implemented in hardware, while others can be implemented in firmware or software that can be executed by a controller, microprocessor, or other computing device. When aspects of embodiments of this disclosure are illustrated or described as block diagrams, flowcharts, or using some other graphical representation, it will be understood that the blocks, apparatuses, systems, techniques, or methods described herein can be implemented as non-limiting examples in hardware, software, firmware, dedicated circuitry or logic, general-purpose hardware or controllers or other computing devices, or some combination thereof.

[0137] The exemplary embodiments of this disclosure described in detail above are merely illustrative and not restrictive. Those skilled in the art will understand that various modifications and combinations can be made to these embodiments or their features without departing from the principles and spirit of this disclosure, and such modifications should fall within the scope of this disclosure.

[0138] Although this disclosure has been described with reference to exemplary embodiments, various changes and modifications may be suggested to those skilled in the art. This disclosure is intended to cover such changes and modifications that fall within the scope of the appended claims.

[0139] Any description in this invention should not be construed as implying that any particular element, step, or function is an essential element that must be included within the scope of the claims. The scope of the patent application subject matter is defined only by the claims.

Claims

1. A method for recommending medical content, comprising: obtaining a first set of medical content, the first set of medical content comprising at least one medical content describing a medical viewpoint, the at least one medical content having a content information density score and a description depth ranking of the medical viewpoint, wherein the information density score indicates a richness of the at least one medical content; obtaining historical data of a user, the historical data comprising a level of understanding ranking of the user of the medical viewpoint described by the at least one medical content; determining a ranking score of the at least one medical content based on the level of understanding ranking of the user of the medical viewpoint described by the at least one medical content and the description depth ranking of the medical viewpoint by the at least one medical content; determining at least one attribute parameter of the at least one medical content, determining a related interaction behavior score of the user for the at least one medical content based on the at least one attribute parameter and the historical data, wherein the historical data further comprises a related interaction behavior of the user previously for the at least one attribute parameter; determining a first weight of the ranking score and a second weight of the related interaction behavior score based on the information density score; obtaining a ranking score of the at least one medical content based on the ranking score, the first weight, the related interaction behavior score, and the second weight; and presenting the at least one medical content to the user in a descending order of the ranking score of the at least one medical content.

2. The method of claim 1, wherein, The determining the ranking score of the at least one medical content comprises: determining a difference between the level of understanding ranking of the user of the medical viewpoint described by the at least one medical content and the description depth ranking of the medical viewpoint by the at least one medical content; and configuring the ranking score of the at least one medical content based on the difference.

3. The method of claim 2, wherein, The determining the ranking score of the at least one medical content comprises: determining whether the difference is within a predetermined difference range; in response to the difference being within the predetermined difference range, configuring a first ranking score for the at least one medical content; and in response to the difference not being within the predetermined difference range, configuring a second ranking score for the at least one medical content, wherein the second ranking score is lower than the first ranking score.

4. The method of claim 3, wherein, The configuring the first ranking score for the at least one medical content comprises: adjusting the first ranking score based on the level of understanding ranking of the user of the medical viewpoint described by the at least one medical content. 5.The method of claim 1, further comprising: in response to one of the at least one medical content describing a plurality of medical viewpoints; determining a plurality of ranking scores for the one medical content respectively for the plurality of medical viewpoints; and determining an average of the plurality of ranking scores as a ranking score of the one medical content. The level of understanding ranking is obtained through an interaction control provided in a medical content previously read by the user, and 6. The method of claim 1, wherein, wherein the interaction control is configured to: ​ in response to a user selecting the interaction control, presenting one or more interaction contents for a medical viewpoint to the user, based on the user's interaction with the one or more interaction contents, determining a level of understanding of the user for the medical viewpoint.

7. The method of claim 6, wherein, the interaction control is configured to: in response to a user obtaining a plurality of levels of understanding for a first medical viewpoint among a plurality of medical viewpoints by selecting a plurality of interaction controls for the first medical viewpoint, determining an average of the plurality of levels of understanding as the level of understanding of the user for the first medical viewpoint.

8. The method of claim 1, wherein, the presenting the at least one medical content to the user in the descending order of the ranking scores of the at least one medical content comprises: in response to the ranking scores of the at least one medical content being the same, presenting the at least one medical content to the user in a descending order of reading volumes of the at least one medical content.

9. The method of claim 1, wherein, the at least one attribute parameter comprises one or more of a drug name and a drug brand.

10. The method of claim 9, wherein, obtaining a ranking score of the at least one medical content comprises: adding a product of the level of understanding score multiplied by the first weight, a product of the associated interaction behavior score multiplied by the second weight, and the information density score to obtain the ranking score of the at least one medical content.

11. The method of claim 9, wherein, the associated interaction behavior comprises a direct behavior, the method further comprising: in response to determining, through the historical data, that the user has the direct behavior for the at least one attribute parameter, directly adjusting the associated interaction behavior score of the medical content corresponding to the at least one attribute parameter.

12. The method of claim 9, wherein, the associated interaction behavior comprises an indirect behavior, the method further comprising: in response to determining, through the historical data, that the user has the indirect behavior for the at least one attribute parameter, determining an interaction degree of the indirect behavior, based on the interaction degree of the indirect behavior, adjusting the associated interaction behavior score of the medical content corresponding to the at least one attribute parameter.

13. The method of claim 9, wherein, the determining the associated interaction behavior score of the at least one medical content for the user comprises: based on the historical data, determining a time interval from a time of occurrence of the associated interaction behavior to a current time, based on the time interval, decaying the associated interaction behavior score.

14. The method of claim 1, wherein, the at least one medical content included in the first set of medical contents comprises a medical content unread by the user, the method further comprising: obtaining a second set of medical contents, the second set of medical contents comprising at least one medical content read by the user, setting the second set of medical contents after the first set of medical contents to present to the user.

15. The method of claim 14, wherein, the method further comprises: determining a publishing time of at least one medical content read by the user, presenting the at least one medical content read by the user to the user in a descending order of the publishing time.

16. The method of claim 1, wherein, a size of the information density score is positively correlated with a size of the first weight.

17. The method of claim 1, wherein, a size of the information density score is negatively correlated with a size of the second weight.

18. An apparatus for recommending medical contents, comprising: a medical content module configured to obtain a first medical content set, the first medical content set comprising at least one medical content describing a medical viewpoint, the at least one medical content having a content information density score and a description depth ranking of the medical viewpoint, wherein the information density score indicates a richness of the at least one medical content; a historical data module configured to obtain historical data of a user, the historical data comprising a level of understanding ranking of the user of a corresponding medical viewpoint; a ranking score module configured to determine a ranking score of the at least one medical content based on the level of understanding ranking of the user of the medical viewpoint described by the at least one medical content and the description depth ranking of the medical viewpoint by the at least one medical content; a related interaction behavior score module configured to determine at least one attribute parameter of the at least one medical content, determine a related interaction behavior score of the user for the at least one medical content based on the at least one attribute parameter and the historical data, wherein the historical data further comprises a related interaction behavior of the user for the at least one attribute parameter previously; a weight module configured to determine a first weight of the ranking score and a second weight of the related interaction behavior score based on the information density score; a ranking module configured to obtain a ranking score of the at least one medical content based on the ranking score, the first weight, the related interaction behavior score, and the second weight; and a content presentation module configured to present the at least one medical content to the user in a descending order of the ranking score of the at least one medical content.

19. A device for recommending medical content, comprising: one or more processors; and one or more memories having stored therein computer-executable programs that, when executed by the processors, perform the method of any one of claims 1-17.

20. A computer program product comprising computer programs or instructions, wherein, The computer program or instructions, when executed by a processor, implement the method of any one of claims 1-17.

21. A computer-readable storage medium having stored thereon computer-executable instructions for implementing the method of any one of claims 1-17 when executed by a processor. The computer program or instructions, when executed by a processor, implement the method of any one of claims 1-17.

21. A computer-readable storage medium having stored thereon computer-executable instructions for implementing the method of any one of claims 1-17 when executed by a processor.

Images