Hand movement training information processing method and related device
By obtaining and analyzing user training data and adjusting the recommended list of hand-function rehabilitation training equipment, the problem of personalized training in the existing technology cannot be carried out according to individual differences in patients, and the rehabilitation training effect is improved.
Patent Information
- Application Number
- CN202411092661.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-09
- Publication Date
- 2024-11-19
- Estimated Expiration
- 2044-08-09
AI Technical Summary
The existing hand function rehabilitation training equipment cannot be personalized according to the specific condition of each patient, resulting in poor rehabilitation training results.
By obtaining the training score and training duration of the target user, determine the historical user scores that are the same as the target user's disease type and the training duration is within the preset range, update the training actions in the recommended list, and determine the confidence relationship based on the user score and training score. Confidence level, adjust the recommendation list to provide a more suitable training program.
The intelligence of the hand function rehabilitation training equipment for training data processing has been improved, the training plan has been optimized, and the patient's rehabilitation training effect has been improved.
Smart Images

Figure CN118629587B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of robotics technology, and in particular to a method for processing hand movement training information and a related device. Background Art
[0002] The hand function rehabilitation training device is mainly used to train the hand joints and is a device used for hand rehabilitation training of patients. When patients perform rehabilitation training based on the existing hand function rehabilitation training device, they perform rehabilitation training based on the pre-configured training movements of the existing hand function rehabilitation training device. However, in actual applications, the condition of each patient may be different, and the pre-configured training movements cannot have a good effect on all patients, resulting in poor rehabilitation training results. Summary of the invention
[0003] The embodiments of the present application provide a method and related device for processing hand movement training information, in order to improve the intelligence of hand function rehabilitation training equipment in processing training data, optimize the training plan of hand function rehabilitation training equipment, and improve the rehabilitation training effect of patients.
[0004] In a first aspect, an embodiment of the present application provides a method for processing hand movement training information, which is applied to a computing device of a hand function training system, wherein the hand function training system includes the computing device and a hand function rehabilitation training apparatus communicatively connected to the computing device, and the method includes:
[0005] Obtaining a training score and training duration of a target user for a target recommended action, wherein the target recommended action is training recommendation content arranged in a recommendation list, and the recommendation list is display content of a training interface displayed by a user terminal associated with the hand function rehabilitation training device;
[0006] Determine a plurality of first historical users according to the training scores and the training durations, wherein the first historical users have the same disease type as the target user, and a difference between the user durations corresponding to the first historical users and the training durations corresponding to the target user is within a preset range;
[0007] Obtaining user scores corresponding to the plurality of first historical users respectively;
[0008] Determining an update strategy for the recommendation list according to the plurality of user scores and the training scores;
[0009] The recommendation list updated according to the update strategy is determined as the display content of the training interface.
[0010] In a possible example of the first aspect, determining an update strategy for the recommendation list according to the plurality of user scores and the training scores includes:
[0011] Determine a confidence relationship according to the user scores respectively corresponding to the plurality of first historical users, wherein the confidence relationship is used to characterize a correspondence between a confidence interval and a confidence level;
[0012] Determining a target confidence interval corresponding to the target recommended action according to the training score;
[0013] Querying a target confidence level corresponding to the target recommended action according to the target confidence interval and the confidence relationship;
[0014] An updating strategy for the recommendation list is determined according to the target confidence level.
[0015] In a possible example of the first aspect, determining the confidence relationship according to the user scores respectively corresponding to the plurality of first historical users includes:
[0016] Determine the median of the user scores respectively corresponding to a plurality of the first historical users;
[0017] Determine the standard deviation of the user scores corresponding to the first historical users whose scores are smaller than the median with respect to the median, and obtain a left standard value;
[0018] Determine the standard deviation of the user scores corresponding to the first historical users that are greater than the median with respect to the median, and obtain a standard value on the right side;
[0019] The confidence relationship is determined according to the left standard value and the right standard value.
[0020] In a possible example of the first aspect, determining an update strategy for the recommendation list according to the target confidence level includes:
[0021] comparing the target confidence level with a preset probability;
[0022] If the target confidence level is greater than the preset probability, determining that the update strategy is to retain the target recommended action corresponding to the training score in the recommendation list;
[0023] If the target confidence level is less than or equal to the preset probability, determining that the update strategy is to delete the target recommended action corresponding to the training score in the recommendation list.
[0024] In a possible example of the first aspect, the determining an update strategy for the recommendation list according to the plurality of user scores and the training scores further includes:
[0025] Acquire multiple custom training actions published by a second historical user, where the second historical user has the same disease type as the target user;
[0026] Obtaining the number of adopters and first action scores respectively corresponding to the plurality of the custom training actions, wherein the first action score is a score of a third historical user with the same disease type as the target user for the custom training action;
[0027] Filtering a target training action from all the custom training actions according to the number of adopters and the first action scores respectively corresponding to the plurality of custom training actions;
[0028] Add the target training action to the recommendation list.
[0029] In a possible example of the first aspect, the adding the target training action to the recommendation list includes:
[0030] When the number of recommendation positions in the recommendation list is less than the number of the target training actions, obtaining the rehabilitation types corresponding to all the target recommended actions and the rehabilitation types of all the target training actions in the recommendation list;
[0031] Filtering out, from the target training movements, the pre-increase recommended movements that are different in rehabilitation type from the target recommended movements;
[0032] Add the number of the recommended positions of the pre-incremented recommended actions to the recommendation list.
[0033] In a possible example of the first aspect, before obtaining the training score and training duration of the target user for the target recommended action, the method further includes:
[0034] Obtain target user's disease information;
[0035] Retrieving a plurality of basic training movements from a database according to the disease information;
[0036] Obtaining second action scores respectively corresponding to the plurality of basic training actions, where the second action scores are scores of the basic training actions by a fourth historical user having the same disease type as the target user;
[0037] Screening the plurality of basic training movements according to the second movement score to obtain the target recommended movement, wherein the target recommended movement is the basic training movement whose second movement score is higher than a preset score;
[0038] Sorting the target recommended actions according to the second action scores from high to low to obtain an action recommendation sequence;
[0039] The target recommended actions are arranged in the recommendation list according to the action recommendation sequence.
[0040] In a second aspect, an embodiment of the present application provides a hand movement training information processing device, which is applied to a computing device of a hand function training system, wherein the hand function training system includes the computing device and a hand function rehabilitation training device that is communicatively connected to the computing device, and the hand movement training information processing device includes:
[0041] A first acquisition unit is used to acquire a training score and a training duration of a target user for a target recommended action, wherein the target recommended action is a training recommendation content arranged in a recommendation list, and the recommendation list is a display content of a training interface displayed by a user terminal associated with the hand function rehabilitation training device;
[0042] A first determining unit is used to determine a plurality of first historical users according to the training scores and the training durations, wherein the first historical users have the same disease type as the target user, and a difference between a user duration corresponding to the first historical users and a training duration corresponding to the target user is within a preset range;
[0043] A second acquisition unit, configured to acquire user scores respectively corresponding to the plurality of first historical users;
[0044] a second determining unit, configured to determine an updating strategy for the recommendation list according to the plurality of user scores and the training scores;
[0045] The third determining unit is used to determine the recommendation list updated according to the update strategy as the display content of the training interface.
[0046] In a third aspect, an embodiment of the present application provides an electronic device, comprising a processor, a memory, a communication interface, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the processor, and the program includes instructions for executing the steps in the first aspect of the embodiment of the present application.
[0047] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium that stores a computer program for electronic data exchange, wherein the computer program enables a computer to execute some or all of the steps described in the first aspect of this embodiment.
[0048] It can be seen that in this embodiment, the computing device obtains the training score and training time of the target user for the target recommended action, the target recommended action is the recommended training content arranged in the recommendation list, and the recommendation list is the display content of the training interface displayed by the user terminal associated with the hand function rehabilitation training device; determines multiple first historical users according to the training score and training time, the first historical users have the same disease type as the target user, and the difference between the user time corresponding to the first historical users and the training time corresponding to the target user is within a preset range; obtains user scores corresponding to the multiple first historical users respectively; determines an update strategy for the recommendation list according to the multiple user scores and the training scores; and determines the recommendation list updated according to the update strategy as the display content of the training interface. It can be seen that the present application determines the update strategy of the recommendation list through multiple user scores and training scores, and determines the recommendation list updated according to the update strategy as the display content of the training interface. The target recommended action can be evaluated according to the training results of patients with the same disease type as the target user and the training results of the target user to obtain the update strategy, thereby obtaining a recommendation list updated according to the update strategy that is more suitable for the target user. This is beneficial to improving the intelligence of the hand function rehabilitation training equipment in processing training data, optimizing the training plan of the hand function rehabilitation training equipment, and improving the rehabilitation training effect of patients. BRIEF DESCRIPTION OF THE DRAWINGS
[0049] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0050] Figure 1 It is a schematic diagram of the architecture of a hand function training system provided in an embodiment of the present application;
[0051] Figure 2 It is a structural schematic diagram of a manipulator provided in an embodiment of the present application;
[0052] Figure 3 It is a flowchart of a method for processing hand movement training information provided by an embodiment of the present application;
[0053] Figure 4 It is a schematic diagram of a training interface provided in an embodiment of the present application;
[0054] Figure 5 is a schematic diagram of another training interface provided in an embodiment of the present application;
[0055] Figure 6is a composition example diagram of an electronic device provided in an embodiment of the present application;
[0056] Figure 7 It is a functional unit composition block diagram of a first hand movement training information processing device provided in an embodiment of the present application;
[0057] Figure 8 It is a block diagram of the functional units of a second hand movement training information processing device provided in an embodiment of the present application. DETAILED DESCRIPTION
[0058] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.
[0059] The terms "first", "second", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices.
[0060] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.
[0061] The embodiments of the present application are described below with reference to the accompanying drawings.
[0062] The technical solution of this application can be applied to Figure 1 The hand function training system 10 shown includes a computing device 110 and a hand function rehabilitation training apparatus 120 .
[0063] The computing device 110 may be a smart phone (such as an Android phone, an iOS phone, a Windows Phone phone, etc.), a smart computer (such as a tablet computer, a PDA, a laptop computer, a desktop computer, etc.), a driving recorder, a server, a mobile Internet device (MID, Mobile Internet Devices) or a wearable device (such as a smart watch, a Bluetooth headset), etc. The above are only examples, not exhaustive, and include but are not limited to the above electronic devices. When the computing device 110 is a server, the server may be an outsourced server, a cloud server, an edge server, an intelligent robot, etc., which are not limited here.
[0064] Among them, hand function rehabilitation training equipment is a rehabilitation training tool. Hand function rehabilitation training equipment is mainly used for continuous passive training activities of metacarpophalangeal joints, proximal interphalangeal joints and distal interphalangeal joints. Based on the theory of neuroplasticity and motor relearning, through repeated task-oriented training of the affected hand, it can promote the reorganization and compensation of the nervous system, enhance the proprioception of the affected hand, induce active movement, prevent muscle atrophy, improve joint mobility, and assist the affected hand to gradually recover fine movements such as grasping, holding, and pinching.
[0065] In a specific implementation, the hand function rehabilitation training device may be configured with a communication unit, which may be used to communicate with a computing device to receive control instructions from the computing device, thereby controlling each joint of the hand function rehabilitation training device to perform training according to parameter information carried in the control instructions. For example, the computing device may be a smart phone or smart computer equipped with control software corresponding to the hand function rehabilitation training device, and the hand function rehabilitation training device may be connected to the computing device via Bluetooth to receive control instructions issued by the computing device.
[0066] Please refer to FIG. 2 , which is a schematic diagram of the structure of a manipulator provided in an embodiment of the present application. Figure 2 The manipulator 20 shown includes a plurality of joint drivers 21, a palm fixing belt 22, and a finger fixing belt 23. Each finger of the manipulator 20 corresponds to at least one joint driver 21. The joint driver 21 outputs driving information based on the control instruction of the computing device 110, so that the corresponding finger on the manipulator moves, so that the manipulator can perform training movements. When the user uses the manipulator for rehabilitation training, the injured hand is bound to the manipulator through the palm fixing belt 22 and the finger fixing belt 23, and then the manipulator performs training movements based on the control instruction, and drives the user's hand to perform corresponding training movements, thereby realizing the user's passive training.
[0067] See also Figure 3 , Figure 3 is a flow chart of a method for processing hand movement training information provided by an embodiment of the present application. The method can be applied in Figure 1 The computing device 110 in the hand function training system shown in FIG. Figure 3 As shown, the hand movement training information processing method includes:
[0068] Step S310, obtaining the training score and training duration of the target user for the target recommended action.
[0069] The target recommended action is the training recommendation content arranged in the recommendation list, and the recommendation list is the display content of the training interface displayed by the user terminal associated with the hand function rehabilitation training device. There are multiple target recommended actions arranged in the recommendation list. In a specific application, the hand movement training information processing method can be used to perform steps S310 to S350 for each target recommended action. Figure 4 In the training interface 410, the content in the dotted box is the training recommended content in the recommendation list. Among them, "two-finger pinch", "three-finger pinch", "side pinch", "hook grip", "column grip", "ball grip" and "compound fist pinch" are multiple target recommended actions in the recommendation list.
[0070] Wherein, when the computing device is a terminal device such as a smart phone or a smart computer, the user terminal may refer to the computing device. Alternatively, when the computing device is a server, the user terminal may be a terminal device configured with control software corresponding to the hand function rehabilitation training device provided by the server, and the user terminal may be connected to the server in communication to implement the relevant functions of the control software. The user terminal may also be connected to the hand function rehabilitation training device in communication to issue control instructions to the hand function rehabilitation training device.
[0071] Among them, the training interface is an application interface provided by the control software corresponding to the hand function rehabilitation training device.
[0072] Among them, the training score is the score of the target user using the hand function rehabilitation training device to perform rehabilitation training for a single target recommended action. Specifically, when the target user only performs one rehabilitation training for a single target recommended action, the training score may be the score of this rehabilitation training. When the target user performs multiple rehabilitation trainings for a single target recommended action, the training score may be the average of the scores of multiple rehabilitation trainings. Among them, the score of rehabilitation training may refer to the comprehensive score of the hand function training system for a single training situation of the target user. Alternatively, the score of rehabilitation training may refer to the self-score of the target user for a single training situation.
[0073] Among them, the training time is the total time that the target user uses the hand function rehabilitation training equipment to perform rehabilitation training for a single target recommended action.
[0074] Step S320: determining a plurality of first historical users according to the training scores and the training duration.
[0075] Among them, the first historical user and the target user have the same disease type, and the difference between the user time corresponding to the first historical user and the training time corresponding to the target user is within a preset range. Specifically, the historical user may refer to a user who has used the hand function rehabilitation training device used by the target user. Alternatively, the historical user may refer to a user who has used a product such as a hand function rehabilitation training device. Among them, the disease type refers to the type of hand injury of the user. For example, the disease type may be a type such as a damaged finger, a damaged ring finger, or a damaged middle finger and ring finger at the same time.
[0076] Specifically, when determining the first historical user, the user duration of each user for the target recommended action can be determined first, and the difference between the duration of the individual user and the training duration of the target user can be determined, and the difference can be compared with a preset range to determine the user whose difference is within the preset range as the first pre-selected historical user. Then, users with the same disease type as the target user can be screened out from the first pre-selected historical users, and the screened users can be determined as the first historical users.
[0077] Or, specifically, when determining the first historical user, the second pre-selected historical user with the same disease type as the target user can be determined first, and then the user time of each second pre-selected historical user for the target recommended action is obtained, and the user time of each second pre-selected historical user is subtracted from the training time of the target user, and then the obtained difference is compared with the preset range, so as to determine the second pre-selected historical user whose difference is within the preset range as the first historical user. This reduces the amount of calculation of the computing device and reduces the processing pressure of the computing device.
[0078] Step S330: Obtain user scores corresponding to the multiple first historical users respectively.
[0079] The user score refers to the score of the rehabilitation training of the first historical user for the target recommended action. A single first historical user has a corresponding user score for the target recommended action. As described above, the score of the rehabilitation training may refer to the comprehensive score of the hand function training system for the single training situation of the first historical user. Alternatively, the score of the rehabilitation training may refer to the self-score of the first historical user for the single training situation.
[0080] Step S340: determining an update strategy for the recommendation list according to the plurality of user scores and the training scores.
[0081] The update strategy is used to update the target recommended action in the recommendation list. Specifically, the update method includes adding a target recommended action or deleting a target recommended action.
[0082] In a specific implementation, the training score of the target user and multiple user scores corresponding to multiple first historical users can be compared to obtain a comparison result, thereby determining the training effect of the target user for the target recommended action based on the comparison result, and then determining the update strategy based on the training effect.
[0083] Step S350: determining the recommendation list updated according to the update strategy as the display content of the training interface.
[0084] In a specific implementation, after determining the update strategy, the training recommendation content in the recommendation list can be updated according to the update strategy, that is, the target recommended action in the recommendation list is updated, and the training recommendation content in the recommendation list after the update is determined as the display content of the training interface.
[0085] It can be seen that in this embodiment, the computing device obtains the training score and training time of the target user for the target recommended action, the target recommended action is the recommended training content arranged in the recommendation list, and the recommendation list is the display content of the training interface displayed by the user terminal associated with the hand function rehabilitation training device; determines multiple first historical users according to the training score and training time, the first historical users have the same disease type as the target user, and the difference between the user time corresponding to the first historical users and the training time corresponding to the target user is within a preset range; obtains user scores corresponding to the multiple first historical users respectively; determines an update strategy for the recommendation list according to the multiple user scores and the training scores; and determines the recommendation list updated according to the update strategy as the display content of the training interface. It can be seen that the present application determines the update strategy of the recommendation list through multiple user scores and training scores, and determines the recommendation list updated according to the update strategy as the display content of the training interface. The target recommended action can be evaluated according to the training results of patients with the same disease type as the target user and the training results of the target user to obtain the update strategy, thereby obtaining a recommendation list updated according to the update strategy that is more suitable for the target user. This is beneficial to improving the intelligence of the hand function rehabilitation training equipment in processing training data, optimizing the training plan of the hand function rehabilitation training equipment, and improving the rehabilitation training effect of patients.
[0086] In one possible example, determining the update strategy of the recommendation list based on the multiple user scores and the training scores includes: determining a confidence relationship based on the user scores corresponding to the multiple first historical users, the confidence relationship being used to characterize the correspondence between a confidence interval and a confidence level; determining a target confidence interval corresponding to the target recommended action based on the training score; querying the target confidence level corresponding to the target recommended action based on the target confidence interval and the confidence relationship; and determining the update strategy of the recommendation list based on the target confidence level.
[0087] The confidence interval refers to the estimated interval of the population parameter constructed by using the user scores corresponding to the multiple first historical users as sample statistics. The confidence level refers to the credible probability of different confidence intervals. The confidence relationship includes the corresponding relationship between each confidence interval in the multiple confidence intervals and its corresponding confidence level.
[0088] In a specific implementation, multiple confidence intervals and confidence levels corresponding to the multiple confidence intervals can be determined based on the average or median of the scores of multiple users and the user score of the first historical user to obtain a confidence relationship. When determining an update strategy for a target recommendation action, the confidence interval in the confidence relationship can be queried based on the training score of the target user to determine the target confidence interval to which the training score corresponds, and then the target confidence level corresponding to the target confidence interval can be determined based on the confidence relationship, thereby determining the update strategy for the recommendation list based on the target confidence level.
[0089] It can be seen that in this example, the confidence relationship is determined by the user scores corresponding to the first historical users, so that the target confidence level of the target user for the target recommended action is determined according to the training score of the target user, and whether the target recommendation list currently including the target recommended action needs to be updated is determined according to the target confidence level. The historical data can be used to determine the situation in which the historical user used the target recommended action for rehabilitation training, so as to compare and contrast the effect of the target user using the target recommended action for rehabilitation training, so as to timely adopt the update strategy according to the fitness of the target user and the target recommended action, adjust the training recommendation content in the recommendation list, adjust the training plan, and improve the flexibility of the computing device in data processing.
[0090] In a possible example, determining the confidence relationship based on the user scores corresponding to the plurality of first historical users respectively includes: determining the median of the user scores corresponding to the plurality of first historical users respectively; determining the standard deviation of the user scores corresponding to the first historical users that are smaller than the median with respect to the median, and obtaining a left standard value; determining the standard deviation of the user scores corresponding to the first historical users that are larger than the median with respect to the median, and obtaining a right standard value; and determining the confidence relationship based on the left standard value and the right standard value.
[0091] The median of multiple user scores refers to the value corresponding to the middle user score when multiple user scores are arranged from large to small. Alternatively, when the number of user scores is an even number, the median of user scores refers to the average of the two middle user scores.
[0092] In a specific implementation, the confidence level calculation device pre-configures data. When determining the confidence relationship, the median of the user scores corresponding to the multiple first historical users can be determined first, and then the error range under each confidence level is calculated based on the multiple user scores and the median, so as to determine the confidence interval corresponding to the confidence level, and then obtain the confidence relationship.
[0093] Specifically, the computing device may be pre-configured with multiple confidence levels and multiples of standard ranges. When determining the confidence relationship, the median of multiple user scores may be determined first, and then the standard deviation of the user score corresponding to the first historical user less than the median is determined for the median to obtain the standard value on the left, and the standard deviation of the user score corresponding to the first historical user greater than the median is determined for the median to obtain the standard value on the right. Then, a confidence interval is determined corresponding to each confidence level and the multiple of the standard range corresponding to the confidence level, thereby obtaining a confidence relationship. For example, the pre-configured multiple confidence levels may be a first confidence level, a second confidence level, and a third confidence level, etc. Among them, in the case of the first confidence level, the confidence interval is a single standard range, that is, the confidence interval corresponding to the first confidence level is from the standard value on the left to the standard value on the right. In the case of the second confidence level, the confidence interval is twice the standard range, that is, the confidence interval corresponding to the second confidence level is twice the standard value on the left to twice the standard value on the right. The confidence interval under the third confidence level is three times the standard range, that is, the confidence interval corresponding to the third confidence level is three times the standard value on the left to three times the standard value on the right.
[0094] It can be seen that in this example, the confidence interval is determined by the median of the user score, thereby obtaining the confidence relationship, which is conducive to improving the accuracy of data adopted by the computing device, improving the credibility of the determined target confidence level, and reducing the impact of skewed distribution.
[0095] In one possible example, determining the update strategy of the recommendation list based on the target confidence level includes: comparing the target confidence level and a preset probability; if the target confidence level is greater than the preset probability, determining that the update strategy is to retain the target recommendation action corresponding to the training score in the recommendation list; if the target confidence level is less than or equal to the preset probability, determining that the update strategy is to delete the target recommendation action corresponding to the training score in the recommendation list.
[0096] Among them, the preset probability is used to characterize the sample credibility standard.
[0097] In a specific implementation, after determining the target confidence level, the target confidence level can be compared with the preset probability. If the target confidence level is greater than the preset probability, it indicates that the training score of the target user using the target recommended action for rehabilitation training is consistent with the user scores of most of the first historical users, and is consistent with normal training conditions. At this time, the update strategy can be determined to retain the target recommended action in the recommendation list, so as to facilitate the target user to continue to select the target recommended action for rehabilitation training. If the comparison result is that the target confidence level is less than or equal to the preset probability, it indicates that the training score of the target user using the target recommended action for rehabilitation training is different from the user scores of most of the first historical users, and the situation of the target user using the target recommended action for rehabilitation training does not conform to the training situation of most of the first historical users, and there is a training risk. At this time, the update strategy can be determined to delete the target recommended action corresponding to the training score from the recommendation list, so that the target user will no longer continue to use the target recommended action for rehabilitation training in the future.
[0098] Specifically, in the implementation, the computing device may also be configured with a standard probability, which is used to characterize the confidence level corresponding to the training standard. For target confidence levels greater than the preset probability, they can be further compared with the standard probability. If the target confidence level is greater than or equal to the standard probability, the corresponding target recommended action can be retained in the recommendation list. If the target confidence level is greater than the preset probability but less than the standard probability, the target recommended action can be deleted from the recommendation list after it is detected that the target user has performed a preset number of rehabilitation trainings using the target recommended action corresponding to the target confidence level. In this way, differentiated update strategies can be further configured corresponding to different confidence level levels to further adapt to the rehabilitation training needs of the target user and improve the intelligence and flexibility of data processing of the computing device.
[0099] It can be seen that in this example, by determining the update strategy to retain the target recommended actions with a target confidence level greater than the preset probability in the recommendation list, and deleting the target recommended actions with a target confidence level less than or equal to the preset probability from the recommendation list, the adaptability of the recommended training content in the recommendation list to the target user can be improved, which is conducive to improving the rehabilitation effect of the target user using hand function rehabilitation training equipment for rehabilitation training.
[0100] In a possible example, the updating strategy of determining the recommendation list based on the multiple user scores and the training scores also includes: obtaining multiple custom training actions posted by a second historical user, the second historical user having the same disease type as the target user; obtaining the number of adopters and the first action score corresponding to the multiple custom training actions, the first action score being the score of the custom training action by a third historical user having the same disease type as the target user; filtering out a target training action from all the custom training actions based on the number of adopters and the first action score corresponding to the multiple custom training actions; and adding the target training action to the recommendation list.
[0101] The customized training action refers to an action in which the second historical user customizes the activity parameters of each joint of the hand function rehabilitation training device.
[0102] Among them, the number of adopters refers to the number of people who use customized training movements for rehabilitation training.
[0103] The first action score may be a user score of a third historical user who has the same disease type as the target user among the number of adopters for the custom training action. Compared with obtaining the user scores of all adopters for the custom training action, this can improve the accuracy of data processing by the computing device and improve the adaptability of the custom training action to the target user.
[0104] In a specific implementation, the number of adopters and the first action scores corresponding to the plurality of custom training actions may be obtained first, and then, based on the number of adopters and the first action score corresponding to each custom training action, it may be determined whether the custom training action meets the preset conditions, and the custom training action meeting the preset conditions may be determined as the target training action. The plurality of custom training actions may be evaluated in accordance with the above method to select the target training action meeting the preset conditions from all the custom training actions.
[0105] Specifically, the preset condition may be that the number of adopters is greater than the first preset number of people, and the score of the first action is higher than the first preset score. Specifically, the computing device may perform the following steps for each custom training action: determine whether the number of adopters corresponding to the custom training action is greater than the first preset number of people, and determine whether the score of the first action corresponding to the custom training action is higher than the first preset score. If the number of adopters is greater than the first preset number of people, and the score of the first action is higher than the first preset score, the custom training action is determined as the target training action. Among them, the following two steps, namely, determining whether the number of adopters corresponding to the custom training action is greater than the first preset number of people, and determining whether the score of the first action corresponding to the custom training action is higher than the first preset score. Can be performed in any order to ensure the orderliness and comprehensiveness of the data processing of the computing device. Alternatively, the above two steps can be performed simultaneously to improve the data processing efficiency of the computing device.
[0106] It can be seen that in this example, by filtering out the target training action from all the custom training actions according to the number of adopters and the first action score corresponding to the custom training action, and adding the target training action to the recommendation list, the richness and adaptability of the training content provided by the computing device to the target user can be improved, thereby optimizing the training plan for the target user. At the same time, by evaluating the custom training action according to the number of adopters and the first action score, the reliability of the computing device's evaluation of the custom training action can be improved, and the adaptability and reliability of the training plan provided by the computing device to the target user can be improved.
[0107] In one possible example, adding the target training action to the recommendation list includes: when the number of recommendation positions in the recommendation list is less than the number of the target training actions, obtaining the rehabilitation types corresponding to all the target recommended actions and the rehabilitation types of all the target training actions in the recommendation list; screening out pre-increment recommended actions that are different from the rehabilitation types of the target recommended actions from the target training actions; and adding the pre-increment recommended actions numbered by the recommendation positions to the recommendation list.
[0108] The number of recommendation positions refers to the number of recommendation positions. A recommendation position refers to a position that can be used to display a target recommended action in a recommendation list in a training interface.
[0109] The rehabilitation type refers to the type of rehabilitation training for different positions of the user's hand according to the injury. For example, if the injury type is the index finger, the rehabilitation type can be the type of rehabilitation training for the index finger alone, the type of rehabilitation training for the index finger and thumb together, the type of rehabilitation training for the index finger and middle finger together, etc.
[0110] In a specific implementation, if the number of recommendation positions in the recommendation list is greater than or equal to the number of target training actions, all target training actions are directly added to the recommendation list. If the number of recommendation positions in the recommendation list is less than the number of target training actions, the rehabilitation types of all the target recommended actions currently in the recommendation list can be determined first, as well as the rehabilitation types of all the target training actions, and then the rehabilitation types of the target recommended actions and the rehabilitation types of the target training actions can be compared, so as to screen out target training actions that are different from the rehabilitation types of the target recommended actions from all the target training actions, and determine them as pre-incremental recommended actions, so as to add the pre-incremental recommended actions to the recommendation list, so as to improve the intelligence of the computing device in data processing, which is conducive to ensuring the comprehensiveness of the training plan for the target user to use the hand function rehabilitation training device.
[0111] Specifically, when adding the pre-increment recommended action to the recommendation list, the size of the pre-increment recommended action and the number of recommendation positions can be compared first. If the number of recommendation positions is greater than or equal to the pre-increment recommended action, all pre-increment recommended actions are directly added to the recommendation list. If the number of recommendation positions is less than the pre-increment recommended action, the pre-increment recommended actions can be sorted in descending order according to the first action score, and the pre-increment recommended actions with the highest number of recommendation positions are added to the recommendation list to ensure the adaptability of the newly added target recommended actions and target users in the recommendation list.
[0112] Alternatively, specifically, if the number of recommendation positions is less than the pre-increment recommended actions, the first parameter may be configured for the number of adopters, the second parameter may be configured for the first action score, and the sum of the product of the number of adopters and the first parameter for each pre-increment recommended action and the product of the first action score and the second parameter may be determined. The pre-increment recommended actions may be sorted in descending order according to the size of the sum of the products of each pre-increment recommended action, and the pre-increment recommended actions with the highest number of recommendation positions in the sorting order may be added to the recommendation list, so as to further improve the intelligence and flexibility of data processing of the computing device, improve the reliability of the newly added target recommended actions in the recommendation list, and ensure the adaptability of the newly added target recommended actions and the target users.
[0113] It can be seen that in this example, when the number of recommendation positions in the recommendation list is less than the number of target training actions, adding target training actions that are different from the rehabilitation type of the target recommended actions to the recommendation list can improve the intelligence and flexibility of the computing device in data processing, which is conducive to ensuring the comprehensiveness of the overall training plan for the target user to use hand function rehabilitation training equipment.
[0114] In a possible example, before obtaining the target user's training score and training duration for the target recommended action, the method also includes: obtaining the target user's disease information; retrieving multiple basic training actions from a database based on the disease information; obtaining second action scores corresponding to the multiple basic training actions, the second action score being a score for the basic training action by a fourth historical user with the same disease type as the target user; screening the multiple basic training actions based on the second action score to obtain the target recommended action, the target recommended action being the basic training action whose second action score is higher than a preset score; sorting the target recommended actions in descending order according to the second action score to obtain an action recommendation sequence; and arranging the target recommended actions in the recommendation list according to the action recommendation sequence.
[0115] The disease information includes the target user's personal information and disease type. The personal information includes the target user's name, gender, age, etc. The basic training action refers to the action stored in the database for rehabilitation training for different disease types. The second action score can be the user score of the basic training action for the fourth historical user who has the same disease type as the target user among all historical users who have used the basic training action.
[0116] In a specific implementation, the database stores multiple basic training actions, and different disease types correspond to multiple different basic training actions. The computing device can determine multiple basic training actions suitable for the disease condition of the target user from the database according to the disease information of the target user.
[0117] Specifically, the basic training actions may include system-set actions and the above-mentioned custom training actions. Figure 5 ,exist Figure 5 In the interface 510 shown, actions such as "double pinch", "triple pinch", and "side pinch" are system-set actions, that is, target recommended actions adapted to the target user determined from the basic training actions. "Customized training action 1" is a customized training action. This "customized training action 1" can be a new action created by the target user by triggering the "new action" control. It can also be an action published by the second historical user and added to the recommendation list as a target training action.
[0118] Specifically, after obtaining the custom training action uploaded by the user, the computing device can monitor the custom training action in real time or regularly. When it is detected that the number of people who adopt the custom training action is higher than the second preset number of people, and the user ratings of the custom training action by all the adopters are higher than the second preset score, the custom training action can be determined as the basic training action and stored in the database for subsequent retrieval and use.
[0119] In a specific implementation, obtaining the second action scores corresponding to the plurality of basic training actions respectively includes: performing the following steps for each basic training action: obtaining all scores of a single basic training action, and filtering out the scores of the fourth historical users with the same disease type as the target user from all the scores, and then determining the average of the scores of all the fourth historical users, and determining the average as the second action score of the basic training action. In this way, the second action score can be used to characterize the user evaluation of the historical users with the same disease type as the target user.
[0120] In a specific implementation, the plurality of basic training actions are screened according to the second action score to obtain the target recommended action, including: performing the following steps for each basic training action: comparing the second action score corresponding to a single basic training action with a preset score, if the second action score corresponding to the basic training action is lower than or equal to the preset score, it indicates that the rehabilitation training effect of the basic training action for the target user's disease type is poor, and at this time, the basic training action may not be recommended to the target user for rehabilitation training. If the second action score corresponding to the basic training action is higher than the preset score, it indicates that the rehabilitation training effect of the basic training action for the target user's disease type is good, and at this time, the basic training action may be determined as the target recommended action and recommended to the target user for rehabilitation training.
[0121] Specifically, after obtaining the target recommended actions, the target recommended actions can be sorted in descending order according to the second action scores to obtain an action recommendation sequence, and the target recommended actions can be arranged in a recommendation list according to the action recommendation sequence to give priority to displaying the target recommended actions with higher rankings in the recommendation list displayed on the training interface.
[0122] It can be seen that in this example, by determining as a target recommended action the basic training action in which the fourth historical user with the same disease type as the target user gives a second action score higher than the preset score, the intelligence of the computing device in data processing can be improved, and the adaptability of the target recommended action to the target user can be improved. At the same time, all target recommended actions are sorted according to the second action score, and the target recommended actions are arranged in the recommendation list according to the action recommendation sequence, so that target recommended actions with higher adaptability can be recommended to the target user first, so as to optimize the recommendation strategy of the training program recommended to the target user, provide the target user with convenience, and improve the training effect.
[0123] The electronic device 60 in the present application may be structured as follows: Figure 6As shown, the electronic device 60 is a computing device, which is a computer or a server, etc., and can be used to execute the above method. Specifically, the electronic device 60 may include a processor 610, a memory 620, a communication interface 630, and one or more programs 621, wherein the one or more programs 621 are stored in the above memory 620 and are configured to be executed by the above processor 610, and the one or more programs 621 include instructions for executing any step in the above method embodiment.
[0124] Among them, the communication interface 630 is used to support the communication between the electronic device 60 and other devices. The processor 610 can be, for example, a central processing unit (CPU), a general processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. It can implement or execute various exemplary logic blocks, units and circuits described in conjunction with the disclosure of the embodiments of the present application. The processor can also be a combination that implements a computing function, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, and the like.
[0125] The memory 620 may be a volatile memory or a nonvolatile memory, or may include both volatile and nonvolatile memories. Among them, the nonvolatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of random access memory 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 (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SynchLink DRAM, SLDRAM), and direct memory bus random access memory (Direct Rambus RAM, DRRAM).
[0126] In a specific implementation, the processor 610 is used to execute any step in the above method embodiment, and when performing data transmission such as sending, the communication interface 630 can be selectively called to complete the corresponding operation.
[0127] It should be noted that the structural diagram of the above-mentioned electronic device 60 is only an example, and the specific components included may be more or less, and no sole limitation is made here.
[0128] The present application can divide the functional units of the electronic device according to the above method example. For example, each functional unit can be divided according to each function, or two or more functions can be integrated into one processing unit. The above integrated unit can be implemented in the form of hardware or in the form of software functional units. It should be noted that the division of units in the embodiments of the present application is schematic and is only a logical function division. There may be other division methods in actual implementation.
[0129] Figure 7 : is a functional unit block diagram of a first hand movement training information processing device provided in an embodiment of the present application. The first hand movement training information processing device 70 includes:
[0130] A first acquisition unit 710 is used to acquire a training score and a training duration of a target user for a target recommended action, where the target recommended action is a training recommendation content arranged in a recommendation list, and the recommendation list is a display content of a training interface displayed by a user terminal associated with the hand function rehabilitation training device;
[0131] A first determining unit 720 is configured to determine a plurality of first historical users according to the training scores and the training durations, wherein the first historical users have the same disease type as the target user, and a difference between the user durations corresponding to the first historical users and the training durations corresponding to the target users is within a preset range;
[0132] The second acquisition unit 730 is used to acquire user scores corresponding to the multiple first historical users respectively;
[0133] A second determining unit 740, configured to determine an updating strategy for the recommendation list according to the plurality of user scores and the training scores;
[0134] The third determining unit 750 is configured to determine the recommendation list updated according to the updating strategy as display content of the training interface.
[0135] In one possible example, in terms of determining the update strategy of the recommendation list based on the multiple user scores and the training scores, the second determination unit is specifically used to: determine a confidence relationship based on the user scores corresponding to the multiple first historical users, the confidence relationship being used to characterize the correspondence between a confidence interval and a confidence level; determine a target confidence interval corresponding to the target recommended action based on the training score; query the target confidence level corresponding to the target recommended action based on the target confidence interval and the confidence relationship; and determine the update strategy of the recommendation list based on the target confidence level.
[0136] In one possible example, in terms of determining the confidence relationship based on the user scores corresponding to the multiple first historical users, the second determination unit is specifically further used to: determine the median of the user scores corresponding to the multiple first historical users; determine the standard deviation of the user scores corresponding to the first historical users that are smaller than the median with respect to the median, and obtain a left-side standard value; determine the standard deviation of the user scores corresponding to the first historical users that are larger than the median with respect to the median, and obtain a right-side standard value; and determine the confidence relationship based on the left-side standard value and the right-side standard value.
[0137] In one possible example, in terms of determining the update strategy of the recommendation list according to the target confidence level, the second determination unit is specifically used to: compare the target confidence level and the preset probability; if the target confidence level is greater than the preset probability, determine that the update strategy is to retain the target recommendation action corresponding to the training score in the recommendation list; if the target confidence level is less than or equal to the preset probability, determine that the update strategy is to delete the target recommendation action corresponding to the training score in the recommendation list.
[0138] In one possible example, in terms of determining the update strategy of the recommendation list based on the multiple user scores and the training scores, the second determination unit is specifically further used to: obtain multiple custom training actions posted by a second historical user, who has the same disease type as the target user; obtain the number of adopters and a first action score corresponding to each of the multiple custom training actions, the first action score being a score of the custom training action by a third historical user who has the same disease type as the target user; filter out a target training action from all the custom training actions based on the number of adopters and the first action scores corresponding to each of the multiple custom training actions; and add the target training action to the recommendation list.
[0139] In one possible example, in terms of adding the target training action to the recommendation list, the second determination unit is further specifically used to: when the number of recommendation positions in the recommendation list is less than the number of the target training actions, obtain the rehabilitation types corresponding to all the target recommended actions in the recommendation list and the rehabilitation types of all the target training actions; filter out pre-increment recommended actions that are different from the rehabilitation types of the target recommended actions from the target training actions; and add the pre-increment recommended actions numbered by the recommendation positions to the recommendation list.
[0140] In one possible example, the first hand movement training information processing device also includes a generation unit, which is used to obtain the target user's disease information before obtaining the target user's training score and training duration for the target recommended action; retrieve multiple basic training actions from a database according to the disease information; obtain second action scores corresponding to the multiple basic training actions, the second action score is the score of the basic training action by a fourth historical user with the same disease type as the target user; filter the multiple basic training actions according to the second action score to obtain the target recommended action, the target recommended action is the basic training action whose second action score is higher than a preset score; sort the target recommended actions in descending order according to the second action score to obtain an action recommendation sequence; and arrange the target recommended actions in the recommendation list according to the action recommendation sequence.
[0141] In the case of using an integrated unit, the functional unit composition block diagram of the second hand movement training information processing device provided in the embodiment of the present application is as follows: Figure 8 As shown. Figure 8 In the embodiment, the second hand motion training information processing device 80 includes: a processing module 820 and a communication module 810. The processing module 820 is used to control and manage the actions of the first hand motion training information processing device, for example, the steps performed by the first acquisition unit 710, the first determination unit 720, the second acquisition unit 730, the second determination unit 740 and the third determination unit 750, and / or other processes for performing the technology described herein. The communication module 810 is used to support the interaction between the second hand motion training information processing device 80 and other devices. Figure 8 As shown, the second hand motion training information processing device 80 may further include a storage module 830 , and the storage module 830 is used to store program codes and data of the second hand motion training information processing device 80 .
[0142] Among them, the processing module 820 can be a processor or a controller, for example, a central processing unit (CPU), a general processor, a digital signal processor (DSP), an ASIC, an FPGA or other programmable logic device, a transistor logic device, a hardware component or any combination thereof. It can implement or execute various exemplary logic blocks, modules and circuits described in conjunction with the disclosure of the embodiments of the present application. The processor can also be a combination that implements a computing function, for example, including a combination of one or more microprocessors, a combination of a DSP and a microprocessor, and the like. The communication module 810 can be a transceiver, an RF circuit or a communication interface, etc. The storage module 830 can be a memory.
[0143] Among them, all relevant contents of each scene involved in the above method embodiment can be referred to the functional description of the corresponding functional module, and will not be repeated here. The above first hand movement training information processing device or the second hand movement training information processing device can execute the above Figure 3 The steps executed by the scheduling server in the hand movement training information processing method shown.
[0144] An embodiment of the present application also provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program for electronic data exchange, wherein the computer program enables a computer to execute part or all of the steps of any method recorded in the above method embodiments, and the above computer includes a server.
[0145] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.
[0146] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.
[0147] In the several embodiments provided in the present application, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of the above-mentioned units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.
[0148] The units described above as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0149] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.
[0150] If the above-mentioned integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a memory, including a number of instructions to enable a computer device (which can be a personal computer, server or network device, etc.) to execute all or part of the steps of the above-mentioned methods in each embodiment of the present application. The aforementioned memory includes: U disk, read-only memory (ROM), random access memory (RAM), mobile hard disk, disk or optical disk and other media that can store program codes.
[0151] A person skilled in the art may understand that all or part of the steps in the various methods of the above embodiments may be completed by instructing the relevant hardware through a program, and the program may be stored in a computer-readable memory, which may include a flash drive, ROM, RAM, a magnetic disk or an optical disk, etc.
[0152] The embodiments of the present application are introduced in detail above. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method and core idea of the present application. At the same time, for general technical personnel in this field, according to the idea of the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.
Claims
1. A method for processing hand movement training information, It is characterized in that A computing device applied to a hand function training system, the hand function training system comprising the computing device and a hand function rehabilitation training apparatus communicatively connected to the computing device, the method comprising: Obtaining a training score and training duration of a target user for a target recommended action, wherein the target recommended action is training recommendation content arranged in a recommendation list, and the recommendation list is display content of a training interface displayed by a user terminal associated with the hand function rehabilitation training device; Determine a plurality of first historical users according to the training scores and the training durations, wherein the first historical users have the same disease type as the target user, and a difference between the user durations corresponding to the first historical users and the training durations corresponding to the target user is within a preset range; Obtaining user scores corresponding to the plurality of first historical users respectively; Determine an update strategy for the recommendation list according to the multiple user scores and the training scores; specifically include: obtaining multiple custom training actions posted by a second historical user, the second historical user having the same disease type as the target user; obtaining the number of adopters and first action scores corresponding to the multiple custom training actions, the first action score being the score of the custom training action by a third historical user having the same disease type as the target user; filtering out a target training action from all the custom training actions according to the number of adopters and the first action scores corresponding to the multiple custom training actions; and adding the target training action to the recommendation list; The recommendation list updated according to the update strategy is determined as the display content of the training interface.
2. The method according to claim 1, It is characterized in that The updating strategy of determining the recommendation list according to the plurality of user scores and the training scores further includes: Determine a confidence relationship according to the user scores respectively corresponding to the plurality of first historical users, wherein the confidence relationship is used to characterize a correspondence between a confidence interval and a confidence level; Determining a target confidence interval corresponding to the target recommended action according to the training score; Querying a target confidence level corresponding to the target recommended action according to the target confidence interval and the confidence relationship; An updating strategy for the recommendation list is determined according to the target confidence level.
3. The method according to claim 2, It is characterized in that The determining the confidence relationship according to the user scores respectively corresponding to the plurality of first historical users includes: Determine the median of the user scores respectively corresponding to a plurality of the first historical users; Determine the standard deviation of the user scores corresponding to the first historical users whose scores are smaller than the median with respect to the median, and obtain a left standard value; Determine the standard deviation of the user scores corresponding to the first historical users that are greater than the median with respect to the median, and obtain a standard value on the right side; The confidence relationship is determined according to the left standard value and the right standard value.
4. The method according to claim 2, It is characterized in that The step of determining an update strategy for the recommendation list according to the target confidence level includes: comparing the target confidence level with a preset probability; If the target confidence level is greater than the preset probability, determining that the update strategy is to retain the target recommended action corresponding to the training score in the recommendation list; If the target confidence level is less than or equal to the preset probability, determining that the update strategy is to delete the target recommended action corresponding to the training score in the recommendation list.
5. The method according to claim 1, It is characterized in that The adding the target training action to the recommendation list includes: When the number of recommendation positions in the recommendation list is less than the number of target training actions, obtaining the rehabilitation types corresponding to all the target recommended actions and the rehabilitation types of all the target training actions in the recommendation list; the number of recommendation positions is used to represent the number of positions that can be used to display the target training actions in the training interface; Filtering out, from the target training movements, the pre-increase recommended movements that are different in rehabilitation type from the target recommended movements; Add the number of the recommended positions of the pre-incremented recommended actions to the recommendation list.
6. The method according to claim 1, It is characterized in that Before obtaining the training score and training duration of the target user for the target recommended action, the method further includes: Obtain target user's disease information; Retrieving a plurality of basic training movements from a database according to the disease information; Obtaining second action scores respectively corresponding to the plurality of basic training actions, where the second action scores are scores of the basic training actions by a fourth historical user having the same disease type as the target user; Screening the plurality of basic training movements according to the second movement score to obtain the target recommended movement, wherein the target recommended movement is the basic training movement whose second movement score is higher than a preset score; Sorting the target recommended actions according to the second action scores from high to low to obtain an action recommendation sequence; The target recommended actions are arranged in the recommendation list according to the action recommendation sequence.
7. A hand movement training information processing device, It is characterized in that A computing device applied to a hand function training system, the hand function training system comprising the computing device and a hand function rehabilitation training apparatus communicatively connected to the computing device, the hand movement training information processing device comprising: A first acquisition unit is used to acquire a training score and a training duration of a target user for a target recommended action, wherein the target recommended action is a training recommendation content arranged in a recommendation list, and the recommendation list is a display content of a training interface displayed by a user terminal associated with the hand function rehabilitation training device; A first determining unit is used to determine a plurality of first historical users according to the training scores and the training durations, wherein the first historical users have the same disease type as the target user, and a difference between a user duration corresponding to the first historical users and a training duration corresponding to the target user is within a preset range; A second acquisition unit, configured to acquire user scores respectively corresponding to the plurality of first historical users; The second determining unit is used to determine the update strategy of the recommendation list according to the multiple user scores and the training scores; specifically used to: obtain multiple custom training actions published by a second historical user, the second historical user has the same disease type as the target user; obtain the number of adopters and the first action score corresponding to the multiple custom training actions, the first action score is the score of the custom training action by a third historical user with the same disease type as the target user; filter out a target training action from all the custom training actions according to the number of adopters and the first action score corresponding to the multiple custom training actions; add the target training action to the recommendation list; The third determining unit is used to determine the recommendation list updated according to the update strategy as the display content of the training interface.
8. An electronic device, It is characterized in that The method comprises a processor, a memory, a communication interface, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the processor, and the programs include instructions for executing the steps in the method according to any one of claims 1 to 6.
9. A computer-readable storage medium, It is characterized in that A computer program for electronic data exchange is stored, wherein the computer program enables a computer to execute the steps in the method according to any one of claims 1 to 6.
Citation Information
Patent Citations
Sports injury rehabilitation training method and system, electronic equipment and medium
CN117238443A
VR experience system and method
CN117406866A
Pension rehabilitation training management system based on massive health
CN117936018A
Recommendation method, computing device and storage medium
US20220092446A1
Software that connects all health facilities, professions and recipients.
US20230307146A1
