Data processing method and device, equipment and storage medium

Abstract

The invention discloses a data processing method and apparatus, a device and a storage medium. The method comprises the steps of collecting user sign data within a preset duration; analyzing the physical sign data of the user to obtain bedridden state data within a preset duration; determining the activity ability level of the user based on the bedridden state data, and determining whether the user sign data is the sign data of the same user based on the bedridden state data to obtain a determination result; and outputting the user activity capability level and the determination result. According to the method, comprehensive evaluation can be carried out through the data within the preset duration, namely, the long-term data, so that the evaluation accuracy of the activity ability of the user can be improved. And moreover, the problem of masquerading during the evaluation period can be avoided, so that the evaluation accuracy of the activity ability of the user can be further improved, the occurrence of evaluation counterfeiting events is reduced, the resource waste is avoided, and the justice and effectiveness of a corresponding system are maintained.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a data processing method, apparatus, device and storage medium. Background Art

[0002] As the aging population continues to grow, the long-term care insurance system has come into being. The long-term care insurance system refers to an insurance system that focuses on solving the basic care needs of the insured population who are in a state of disability for a long time. Therefore, the assessment of the activity level of the insured is an important part of the long-term care insurance system. Its accuracy and fairness are related to the rights and interests of each beneficiary and the healthy operation of the entire system.

[0003] In actual applications, the above-mentioned user activity ability level is used to indicate the degree of limitation of the insured person's activity ability. For example, user activity ability can generally be divided into mild disability, moderate disability and severe disability. The more severe the insured person's user activity ability level, the higher the insurance level will be provided by the long-term care insurance system. Therefore, in the practice of long-term care insurance, there are frequent incidents of fraud in the assessment of user activity ability level, which not only causes a waste of resources, but also seriously erodes the fairness and effectiveness of the system. Summary of the invention

[0004] The embodiments of the present application provide a data processing method, apparatus, device and storage medium to accurately evaluate user activity capabilities and reduce the occurrence of evaluation fraud incidents, thereby avoiding waste of resources and maintaining the fairness and effectiveness of the corresponding system.

[0005] In a first aspect, an embodiment of the present application provides a data processing method, including:

[0006] Collect user's vital sign data within a preset time period;

[0007] Analyze the user's vital sign data to obtain bed rest status data within the preset time period;

[0008] Determine the user's activity level based on the bed-ridden state data, and determine whether the user's vital sign data are vital sign data of the same user based on the bed-ridden state data, to obtain a determination result;

[0009] The user activity ability level and the determination result are output.

[0010] Optionally, the user vital sign data includes time point information indicating that the user switches between the bed-lying state and the out-of-bed state within the preset time period;

[0011] The step of analyzing the user's vital sign data to obtain the bed rest status data within the preset time period includes:

[0012] Analyze the time point information to determine the sum of multiple time periods during which the user is in bed within the preset time period, and the sum of time periods greater than a first time period among the multiple time periods during which the user is in bed within the preset time period, where the first time period is used to indicate a minimum duration during which the user is in bed;

[0013] Determine, based on the sum of the multiple time periods and the sum of the time periods greater than the first time period, a frequency of the user switching between the lying-in-bed state and the getting-out-of-bed state within the preset time period;

[0014] A sum of the multiple time periods and the frequency is determined as the bed state data.

[0015] Optionally, determining the user's activity level based on the bed status data includes:

[0016] When the sum of the multiple time periods is greater than the second duration and less than the third duration, and the frequency is greater than the first frequency and less than the second frequency, the user activity ability level is determined to be the first level;

[0017] When the sum of the multiple time periods is greater than the third duration and less than the fourth duration, and the frequency is greater than the second frequency and less than the third frequency, determining the user activity level as the second level;

[0018] When the sum of the multiple time periods is greater than a fourth time period and the frequency is greater than a third frequency, determining the user activity ability level as a third level;

[0019] Among them, the second duration is smaller than the third duration, the third duration is smaller than the third duration, the first frequency is smaller than the second frequency, the second frequency is smaller than the third frequency, the user activity ability represented by the first level is higher than the user activity ability represented by the second level, and the user activity ability represented by the second level is higher than the user activity ability represented by the third level.

[0020] Optionally, the user vital sign data includes time point information indicating that the user switches between the bed-lying state and the out-of-bed state within the preset time period, and basic vital sign data of the user in the bed-lying state within the preset time period;

[0021] The step of analyzing the user's vital sign data to obtain the bed rest status data within the preset time period includes:

[0022] Analyze the time point information to determine multiple time periods during which the user is in bed within the preset time period;

[0023] Determine, from the multiple time periods during which the user is in bed within the preset time period, multiple time periods greater than a fifth time period;

[0024] Based on the multiple time periods greater than the fifth time period, processing the basic vital sign data of the user in the bed-resting state within the preset time period, and determining an array of vital sign data of the user in the bed-resting state within two adjacent time periods among the multiple time periods greater than the fifth time period;

[0025] The vital sign data arrays of the user in the bed-resting state in the two adjacent time periods are processed to obtain a processed array, and the processed array is used as the bed-resting state data.

[0026] Optionally, the processing of the vital sign data arrays of the user in the bed-resting state in the two adjacent time periods to obtain a processed array includes:

[0027] Determine the sum of the array lengths of the vital sign data arrays of the user in the bed-resting state in the two adjacent time periods;

[0028] The array of vital sign data of the user in the bed-resting state in the two adjacent time periods is stretched to the sum of the array lengths to obtain the processed array.

[0029] Optionally, the bed-lying state includes a wakeful state and a sleeping state, and the sleeping state includes a rapid eye movement state, a light sleep state, and a deep sleep state;

[0030] The step of stretching the array of vital sign data of the user in the bed-resting state in the two adjacent time periods to the sum of the array lengths to obtain the processed array comprises:

[0031] Lengthening the array of vital sign data of the user in the awake state in the previous time period of the two adjacent time periods to the sum of the array lengths to obtain a first processed array;

[0032] Lengthening the arrays of the user's vital sign data in the rapid eye movement state, the light sleep state, and the deep sleep state in the previous time period of the two adjacent time periods to the sum of the array lengths to obtain a second processed array;

[0033] The vital sign data arrays of the user in the awake state, the rapid eye movement state, the light sleep state and the deep sleep state in the latter time period of the two adjacent time periods are stretched to the sum of the array lengths to obtain a third processed array.

[0034] Optionally, before determining whether the user vital sign data is vital sign data of the same user based on the bed status data, the method further includes:

[0035] The vital sign data arrays of the user in the awake state, the rapid eye movement state, the light sleep state and the deep sleep state in the previous time period of the two adjacent time periods are stretched to the sum of the array lengths to obtain a fourth processed array;

[0036] The determining, based on the bed state data, whether the user vital sign data is vital sign data of the same user, and obtaining a determination result, comprises:

[0037] Based on the first processed array, the second processed array and the third processed array, a contrast loss value corresponding to the NT-Xent function is determined by a normalized temperature cross entropy NT-Xent function; and based on the first processed array, the second processed array and the fourth processed array, a contrast loss reference value corresponding to the NT-Xent function is determined by the NT-Xent function;

[0038] Based on the contrast loss value and the contrast loss reference value, it is determined whether the user vital sign data is the vital sign data of the same user to obtain the determination result.

[0039] In a second aspect, an embodiment of the present application provides a data processing device, including:

[0040] A data collection module is used to collect user vital sign data within a preset time period;

[0041] A data analysis module, used to analyze the user's vital sign data to obtain bed rest status data within the preset time period;

[0042] a data determination module, used to determine the user's activity level based on the bed state data, and to determine whether the user's vital sign data are vital sign data of the same user based on the bed state data, to obtain a determination result;

[0043] A data output module is used to output the user activity ability level and the determination result.

[0044] In a third aspect, an embodiment of the present application provides an electronic device, the device comprising: a processor, a memory, and a system bus;

[0045] The processor and the memory are connected via the system bus;

[0046] The memory is used to store a program, wherein the program includes instructions, and when the instructions are executed by the processor, the processor executes any implementation step of the above-mentioned data processing method based on weak measurement technology.

[0047] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, in which instructions are stored. When the instructions are executed on an electronic device, the electronic device executes any implementation step of the above-mentioned data processing method based on weak measurement technology.

[0048] It can be seen from the above technical solutions that the embodiments of the present application have the following advantages:

[0049] In an embodiment of the present application, after collecting the user's vital sign data within a preset time, the user's vital sign data can be analyzed first to obtain the bed state data within the preset time, and then the user's activity ability level is determined based on the bed state data, and whether the user's vital sign data is the vital sign data of the same user is determined based on the bed state data to obtain a determination result, so that the user's activity ability level and the determination result can be output. It can be seen that compared with manual evaluation based on the currently observed user state, the above method can be used to conduct a comprehensive evaluation through data within a preset time, that is, longer-term data, thereby helping to improve the accuracy of the user's activity ability evaluation. In addition, the bed state data can be used to further determine whether the collected user's vital sign data is the data of the same user, which helps to avoid the problem of impersonation during the evaluation period, thereby further improving the accuracy of the user's activity ability evaluation, and reducing the occurrence of evaluation fraud, thereby avoiding waste of resources and maintaining the fairness and effectiveness of the corresponding system. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 A flowchart of a data processing method provided in an embodiment of the present application;

[0051] Figure 2 A schematic diagram of the structure of a data processing device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0052] As mentioned above, in actual applications, the above-mentioned user activity ability level is used to indicate the degree of limitation of the insured person's activity ability. For example, user activity ability can generally be divided into mild disability, moderate disability and severe disability. The more severe the insured person's user activity ability level, the higher the insurance level will be provided by the long-term care insurance system. Therefore, in the practice of long-term care insurance, there are frequent incidents of fraud in the assessment of user activity ability level, which not only causes a waste of resources, but also seriously erodes the fairness and effectiveness of the system.

[0053] Specifically, the current assessment of user activity capabilities generally relies on staff visiting users. Therefore, it is difficult to truly understand the user's status and it is easy to be deliberately falsified, such as maliciously feigning illness or impersonating others.

[0054] Based on this, in order to solve the above problems, an embodiment of the present application provides a data processing method, which may include: after collecting user vital sign data within a preset time period, the user vital sign data may be first analyzed to obtain bed status data within the preset time period, and then the user's activity ability level is determined based on the bed status data, and whether the user vital sign data is the vital sign data of the same user is determined based on the bed status data to obtain a determination result, so that the user's activity ability level and the determination result can be output.

[0055] It can be seen that compared with manual evaluation based on the currently observed user status, the above method can make a comprehensive evaluation through data within a preset time period, that is, longer-term data, which helps to improve the accuracy of the user's activity ability evaluation. In addition, the use of bed status data can further determine whether the collected user vital sign data is the data of the same user, which helps to avoid the problem of impersonation during the evaluation period, thereby further improving the accuracy of the user's activity ability evaluation and reducing the occurrence of evaluation fraud, thereby avoiding waste of resources and maintaining the fairness and effectiveness of the corresponding system.

[0056] It should be noted that the embodiments of the present application may not limit the execution subject of the data processing method. For example, the data processing method of the embodiments of the present application may be applied to data processing devices such as terminal devices or servers. Among them, the terminal device may be an electronic device such as a smart phone, a computer, a personal digital assistant (PDA), a tablet computer, etc. The server may be an independent server, a cluster server, or a cloud server.

[0057] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, 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.

[0058] Figure 1 A flowchart of a data processing method provided in an embodiment of the present application. Figure 1 As shown, the data processing method provided in the embodiment of the present application uses the corresponding data processing device as the execution subject to describe the specific implementation of the solution. The data processing method may include the following steps S101-S103.

[0059] S101: Collecting user's vital sign data within a preset time period.

[0060] User vital sign data refers to the vital sign data of the object to be evaluated. In the embodiment of the present application, the corresponding user vital sign data can be collected by installing a millimeter wave radar device for the object to be evaluated. Accordingly, the millimeter wave radar device can be connected to a data processing device to send the collected user vital sign data to the data processing device.

[0061] Among them, the above-mentioned user vital sign data may include multiple types of data. After the millimeter wave radar device is powered on, it can continuously collect data and send the collected data to the data processing device at a preset frequency. Among them, the preset frequency is, for example, 1 minute / time. For ease of understanding, the collected user vital sign data is exemplarily described below in conjunction with Table 1.

[0062] Table 1

[0063]

[0064]

[0065] It should be noted that in the above Table 1, the user vital sign data collected by the millimeter wave radar device may include the above six types A, B, D, E, H and R, and the data represented by sequence number 3 is not user vital sign data.

[0066] In addition, the user vital sign data represented by sequence number 1 can also indicate the time point information when the user switches between the bed-lying state and the out-of-bed state. Therefore, the user vital sign data may include the time point information indicating the user switches between the bed-lying state and the out-of-bed state every day. For example, at 8:00 a.m. on a certain day, the value of the data corresponding to sequence number 1 is 1, indicating that someone is in bed, that is, the user is in bed; at 9:15 a.m., the value of the data corresponding to sequence number 1 is 0, indicating that no one is in bed, that is, the user is out of bed; at 9:30 a.m., the value of the data corresponding to sequence number 1 is 1, indicating that someone is in bed, that is, the user is in bed; at 12:30 a.m., the value of the data corresponding to sequence number 1 is 0, indicating that no one is in bed, that is, the user is out of bed.

[0067] Accordingly, in order to collect longer-term user vital sign data to comprehensively evaluate the user's activity ability, thereby improving the accuracy of the evaluation, in the embodiment of the present application, the user vital sign data within the above-mentioned preset time length can be collected. For example, the preset time length can be 1 day or 24 hours, that is, the daily user vital sign data can be collected and converted into a one-dimensional array arranged in time sequence. Furthermore, the preset time length can also be multiple consecutive days, so after collecting the user vital sign data for multiple consecutive days, it can be divided and processed according to each day to obtain multiple corresponding one-dimensional arrays.

[0068] S102: Analyze the user's vital sign data to obtain bed rest status data within a preset time period.

[0069] As an example, as mentioned above, the user vital sign data may include time point information indicating that the user switches between the bed-lying state and the out-of-bed state within a preset time period.

[0070] Based on this, when obtaining the bed resting state data within the preset duration, first, the above time point information can be analyzed to determine the sum of multiple time periods in which the user is in bed resting state within the preset duration, and the sum of time periods greater than the first time period among the multiple time periods in which the user is in bed resting state within the preset duration. The above first time period is used to indicate the minimum duration of the user being in bed resting state, for example, 300 seconds. Therefore, the time period greater than 300 seconds can be screened out from the multiple time periods in which the user is in bed resting state within the preset duration, and the screened time period can indicate the time period in which the user is continuously in bed resting.

[0071] Since the user may switch between the bed-lying state and the out-of-bed state every day, by analyzing the above time points, multiple time periods in which the user is in the bed-lying state within the preset duration can be counted. In practical applications, the multiple time periods may include the duration of time the user switches from the bed-lying state to the out-of-bed state. In addition, if the user continues to stay in the bed after switching from the out-of-bed state to the bed-lying state, the multiple time periods may also include the duration of time the user continues to stay in the bed until the end of the day's collection. In this way, the duration of the user being in the bed-lying state within the preset duration can be calculated through the above multiple time periods, that is, the sum of multiple time periods, and the time period greater than the first duration can be screened out from the multiple time periods, and the sum of the time periods greater than the first duration can be calculated.

[0072] Next, when obtaining the bed status data within the preset duration, the frequency of the user switching between the bed-lying state and the out-of-bed state within the preset duration can be determined based on the fact that the sum of the multiple time periods obtained above is greater than the sum of the time periods of the first duration, thereby determining the sum of the multiple time periods and the frequency as the bed status data.

[0073] In specific implementation, the sum of time periods greater than the first duration can be divided by the sum of multiple time periods. As mentioned above, a time period greater than the first duration can represent a time period in which the user has been lying in bed. Therefore, through the above calculation method, the result can be used as the frequency of the user switching between the lying state and the out-of-bed state within the preset duration. Accordingly, the larger the value of the frequency, the worse the user's mobility and the more severe the disability; and the smaller the value of the frequency, the stronger the user's mobility and the lighter the disability.

[0074] As another example, combined with the above Table 1, since the user vital signs data can also include data representing a variety of different bed states and basic vital signs data such as the user's breathing, heart rate and body movement, wherein the various different bed states include awake state and sleep state, and the sleep state includes rapid eye movement state, shallow sleep state and deep sleep state, therefore, the above user vital signs data can also be divided according to a variety of different bed states, that is, including the basic vital signs data of the user in a variety of different bed states within a preset duration. For example, the above user vital signs data can include basic vital signs data such as the user's heart rate, breathing and body movement data in the awake state within a preset duration, basic vital signs data such as the heart rate, breathing and body movement data in the rapid eye movement state, heart rate, breathing and body movement data in the shallow sleep state, and basic vital signs data such as the heart rate, breathing and body movement data in the deep sleep state.

[0075] Based on this, when obtaining the bed resting state data within the preset time length, first, the time point information can be analyzed to determine multiple time periods in which the user is in the bed resting state within the preset time length. For this, please refer to the above-mentioned related description, which will not be repeated here.

[0076] Next, multiple time periods greater than a fifth time period may be determined from multiple time periods during which the user is in bed within the preset time period, where the fifth time period is, for example, 30 minutes.

[0077] Then, based on the above-mentioned multiple time periods greater than the fifth time period, the basic vital sign data of the user in bed in the preset time period can be processed to determine the vital sign data array of the user in bed in two adjacent time periods in the multiple time periods greater than the fifth time period. For example, array a (including a1, a2, a3 and a4) represents the vital sign data array of the user in bed in the previous time period of two adjacent time periods, and array b (including b1, b2, b3 and b4) represents the vital sign data array of the user in bed in the next time period of two adjacent time periods. Then, the vital sign data arrays corresponding to the user in the two adjacent time periods can be embodied in the following form:

[0078] (a1: awake state, heart rate 56.3, respiration 23.5, body movement data 1;

[0079] …

[0080] a2: rapid eye movement state, heart rate 55.6, respiration 22.5, body movement data 2;

[0081] …

[0082] a3: Light sleep state, heart rate 55.3, respiration 22.1, body movement data 0;

[0083] …

[0084] a4: Deep sleep state, heart rate 55.1, respiration 21.5, body movement data 0.

[0085] …)

[0086] (b1: awake state, heart rate 76.3, respiration 18.5, body movement data 2;

[0087] …

[0088] b2: rapid eye movement state, heart rate 75.6, respiration 17.5, body movement data 2;

[0089] …

[0090] b3: Light sleep state, heart rate 75.3, respiration 17.1, body movement data 1;

[0091] …

[0092] b4: Deep sleep state, heart rate 75.1, respiration 16.5, body movement data 0.

[0093] …)

[0094] Among them, each array can be arranged in time sequence, so “…” represents the data corresponding to other time points, which will not be expanded here.

[0095] Then, the array of vital sign data of the user in bed in two adjacent time periods can be processed to obtain a processed array, so as to use the processed array as bed state data. The processing of the array of vital sign data can be embodied as a stretching operation, and the stretching operation can be embodied as selecting a random number between two adjacent elements in the array for filling.

[0096] Accordingly, in a specific implementation, first, the sum of the array lengths of the user's vital sign data arrays in bed in two adjacent time periods can be determined. In combination with the above example, the sum of the array lengths corresponding to array a and array b is determined.

[0097] Next, the array of vital sign data of the user in bed in two adjacent time periods can be stretched to the sum of the lengths of the arrays to obtain a processed array.

[0098] Furthermore, as mentioned above, the bed-lying state includes the awake state and the sleeping state, and the sleeping state includes the rapid eye movement state, the light sleep state and the deep sleep state. Based on this, the array of vital sign data of the user in the bed-lying state in two adjacent time periods is stretched to the sum of the array lengths, which can be specifically embodied as follows: the array of vital sign data of the user in the awake state on the previous day of two consecutive days is stretched to the sum of the array lengths to obtain the first processed array, that is, the array a1 is stretched to obtain the first processed array z i In addition, the arrays of the user's physical sign data in the rapid eye movement state, the light sleep state, and the deep sleep state on the previous day of the two consecutive days can be stretched to the sum of the array lengths to obtain the second processed array, that is, the arrays a2, a3, and a4 are stretched to obtain the second processed array z j Furthermore, the arrays of the user's vital sign data in the wakefulness state, rapid eye movement state, light sleep state, and deep sleep state on the second day of the two consecutive days can be stretched to the sum of the array lengths to obtain a third processed array, that is, the arrays b1, b2, b3, and b4 are stretched to obtain the third processed array z k .

[0099] S103: Determine the activity level of the user based on the bed-ridden state data, and determine whether the user vital sign data is the vital sign data of the same user based on the bed-ridden state data to obtain a determination result.

[0100] In the embodiment of the present application, the bed state data may include the sum of multiple time periods in which the user is in bed within the preset duration and the frequency of switching between the bed state and the out-of-bed state within the preset duration. Based on this, since the information related to the duration and frequency of the user's bed rest can indicate whether the user is bedridden for a long time, and the user's activity level can also be reflected by whether the user is bedridden for a long time, therefore, judging the user's activity ability through the above bed state data is helpful to improve the accuracy of the assessment of the user's activity ability.

[0101] Based on this, in the process of determining the user's activity level based on the bed state data, when the sum of multiple time periods is greater than the second duration and less than the third duration, and the frequency is greater than the first frequency and less than the second frequency, the user's activity level can be determined as the first level; when the sum of multiple time periods is greater than the third duration and less than the fourth duration, and the frequency is greater than the second frequency and less than the third frequency, the user's activity level can be determined as the second level; when the sum of multiple time periods is greater than the fourth duration, and the frequency is greater than the third frequency, the user's activity level can be determined as the third level. Among them, the second duration is less than the third duration, the third duration is less than the third duration, the first frequency is less than the second frequency, the second frequency is less than the third frequency, the user's activity level represented by the first level is higher than the user's activity level represented by the second level, and the user's activity level represented by the second level is higher than the user's activity level represented by the third level.

[0102] For example, in actual applications, the value of the second duration is, for example, 10 hours, the value of the third duration is, for example, 12 hours, the value of the fourth duration is, for example, 18 hours, the value of the first frequency is, for example, 0.88, the value of the second frequency is, for example, 0.90, and the value of the third frequency is, for example, 0.96. Accordingly, the first level, for example, indicates that the user has strong mobility and is in a mild disability state, the second level, for example, indicates that the user has average mobility and is in a moderate disability state, and the third level, for example, indicates that the user has poor mobility and is in a severe disability state. That is to say, when the sum of the above-mentioned multiple intervals is greater than 10 hours and less than 12 hours, and the above-mentioned probability is greater than 0.88 and less than 0.90, it can be determined that the user activity ability of the object to be evaluated is relatively strong and is in a mild disability state; when the sum of the above-mentioned multiple intervals is greater than 12 hours and less than 18 hours, and the above-mentioned probability is greater than 0.90 and less than 0.96, it can be determined that the user activity ability of the object to be evaluated is average and is in a moderate disability state; when the sum of the above-mentioned multiple intervals is greater than 18 hours and the above-mentioned probability is greater than 0.96, it can be determined that the user activity ability of the object to be evaluated is relatively poor and is in a severe disability state.

[0103] Furthermore, in an embodiment of the present application, in order to determine whether the user vital sign data collected above is the vital sign data of the same user, the normalized temperature-scaled cross-entropy loss (NT-Xent) function can be used to compare the similarity of the vital sign data arrays of the user in a variety of different bed resting states in two adjacent time periods. It can be determined whether the data of the two adjacent time periods are the data of the same user, thereby further improving the accuracy of the assessment of the user's activity ability and reducing the occurrence of assessment fraud, thereby avoiding waste of resources and maintaining the fairness and effectiveness of the corresponding system.

[0104] Based on this, before determining whether the user vital sign data is the vital sign data of the same user based on the above-mentioned bed-lying state data, the vital sign data arrays of the user in the awake state, rapid eye movement state, light sleep state and deep sleep state in the previous time period of two adjacent time periods can be stretched to the sum of the array lengths to obtain a fourth processed array, that is, the arrays a1, a2, a3 and a4 are stretched to obtain the fourth processed array z k '.

[0105] Accordingly, when determining whether the user's vital sign data is the vital sign data of the same user based on the above-mentioned bed state data, the first processing array z i , the second processing array z j and the third processing array z k , determine the contrast loss value of the NT-Xent function through the NT-Xent function, and then based on the first processing array z i , the second processing array z j and the fourth processing array z k ', determine the contrast loss benchmark value corresponding to the NT-Xent function through the NT-Xent function.

[0106] For ease of understanding, the calculation process of the contrast loss value corresponding to the NT-Xent function is introduced below in combination with the following formula (1).

[0107]

[0108] Among them, l i,j represents the contrast loss value of the NT-Xent function, sim() represents the cosine similarity, z i represents the first processing array, z j represents the second processing array, z k represents the third processing array, τ represents the temperature parameter used to adjust the scale, and N represents the time length, which is the sum of the above array lengths.

[0109] Accordingly, the calculation process of the contrast loss benchmark value corresponding to the NT-Xent function is introduced below in combination with formula (2).

[0110]

[0111] Among them, l i,j ′ represents the comparison loss benchmark value of the NT-Xent function, sim() represents the cosine similarity, z i represents the first processing array, z j represents the second processing array, z k′ represents the fourth processing array, τ represents the temperature parameter used to adjust the scale, and N represents the time length, that is, the data length.

[0112] Furthermore, after the contrast loss value and the contrast loss reference value are determined, it can be determined whether the user vital sign data are vital sign data of the same user based on the contrast loss value and the contrast loss reference value.

[0113] For example, the process of determining whether user vital sign data is vital sign data of the same user is described below in conjunction with formula (3).

[0114]

[0115] Among them, t represents the experience value, l i,j ′ represents the contrast loss benchmark value of the NT-Xent function, l i,j Represents the contrast loss value of the NT-Xent function.

[0116] Correspondingly, when the experience value t is greater than a preset experience value, it can be determined that the user's vital sign data is not the vital sign data of the same user, that is, there is an impersonation problem. The preset experience value is, for example, 0.15.

[0117] S104: Output the user's activity ability level and determination result.

[0118] Based on the relevant contents of the above steps S101-S104, it can be known that in the embodiment of the present application, after collecting the user's vital sign data within the preset time, the user's vital sign data can be analyzed first to obtain the bed state data within the preset time, and then the user's activity ability level is determined based on the bed state data, and whether the user's vital sign data is the vital sign data of the same user is determined based on the bed state data to obtain the determination result, so that the user's activity ability level and the determination result can be output. It can be seen that compared with manual evaluation based on the currently observed user state, the above method can be comprehensively evaluated through the data within the preset time, that is, the longer-term data, thereby helping to improve the accuracy of the evaluation of the user's activity ability. In addition, the bed state data can be used to further determine whether the collected user's vital sign data is the data of the same user, which helps to avoid the problem of impersonation during the evaluation period, thereby further improving the accuracy of the evaluation of the user's activity ability, and reducing the occurrence of evaluation fraud, thereby avoiding waste of resources and maintaining the fairness and effectiveness of the corresponding system.

[0119] Furthermore, based on the data processing method provided in the above embodiment, the embodiment of the present application can also provide a data processing device. The data processing device is described below in conjunction with the embodiments and drawings.

[0120] Figure 2A schematic diagram of the structure of a data processing device provided in an embodiment of the present application. Figure 2 As shown, the data processing device 200 provided in the embodiment of the present application may include:

[0121] The data collection module 201 is used to collect the user's vital sign data within a preset time period;

[0122] The data analysis module 202 is used to analyze the user's vital sign data to obtain the bed rest status data within the preset time period;

[0123] A data determination module 203 is used to determine the user's activity level based on the bed state data, and to determine whether the user's vital sign data are vital sign data of the same user based on the bed state data, to obtain a determination result;

[0124] The data output module 204 is used to output the user activity ability level and the determination result.

[0125] Optionally, the user vital sign data includes time point information indicating that the user switches between the bed-lying state and the out-of-bed state within the preset time period;

[0126] The data analysis module 202 is specifically used for:

[0127] Analyze the time point information to determine the sum of multiple time periods during which the user is in bed within the preset time period, and the sum of time periods greater than a first time period among the multiple time periods during which the user is in bed within the preset time period, where the first time period is used to indicate a minimum duration during which the user is in bed;

[0128] Determine, based on the sum of the multiple time periods and the sum of the time periods greater than the first time period, a frequency of the user switching between the lying-in-bed state and the getting-out-of-bed state within the preset time period;

[0129] A sum of the multiple time periods and the frequency is determined as the bed state data.

[0130] Optionally, the data determination module 203 is specifically configured to:

[0131] When the sum of the multiple time periods is greater than the second duration and less than the third duration, and the frequency is greater than the first frequency and less than the second frequency, the user activity ability level is determined to be the first level;

[0132] When the sum of the multiple time periods is greater than the third duration and less than the fourth duration, and the frequency is greater than the second frequency and less than the third frequency, determining the user activity level as the second level;

[0133] When the sum of the multiple time periods is greater than a fourth time period and the frequency is greater than a third frequency, determining the user activity ability level as a third level;

[0134] Among them, the second duration is smaller than the third duration, the third duration is smaller than the third duration, the first frequency is smaller than the second frequency, the second frequency is smaller than the third frequency, the user activity ability represented by the first level is higher than the user activity ability represented by the second level, and the user activity ability represented by the second level is higher than the user activity ability represented by the third level.

[0135] Optionally, the user vital sign data includes time point information indicating that the user switches between the bed-lying state and the out-of-bed state within the preset time period, and basic vital sign data of the user in the bed-lying state within the preset time period;

[0136] The data analysis module 202 includes:

[0137] A time point information analysis module, used to analyze the time point information and determine multiple time periods during which the user is in bed within the preset time period;

[0138] a time period determination module, configured to determine a plurality of time periods greater than a fifth time period from a plurality of time periods during which the user is in bed within the preset time period;

[0139] a vital sign data processing module, configured to process the basic vital sign data of the user in bed within the preset time period based on the multiple time periods greater than the fifth time period, and determine an array of vital sign data of the user in bed within two adjacent time periods among the multiple time periods greater than the fifth time period;

[0140] The array processing module is used to process the vital sign data array of the user in the bed-resting state in the two adjacent time periods to obtain a processed array, and use the processed array as the bed-resting state data.

[0141] Optionally, the array processing module includes:

[0142] A length determination module, used to determine the sum of the array lengths of the vital sign data arrays of the user in the bed-resting state in the two adjacent time periods;

[0143] The array lengthening module is used to lengthen the array of vital sign data of the user in the bed-resting state in the two adjacent time periods to the sum of the array lengths to obtain the processed array.

[0144] Optionally, the bed-lying state includes a wakeful state and a sleeping state, and the sleeping state includes a rapid eye movement state, a light sleep state, and a deep sleep state;

[0145] The array lengthening module is specifically used for:

[0146] Lengthening the array of vital sign data of the user in the awake state in the previous time period of the two adjacent time periods to the sum of the array lengths to obtain a first processed array;

[0147] Lengthening the arrays of the user's vital sign data in the rapid eye movement state, the light sleep state, and the deep sleep state in the previous time period of the two adjacent time periods to the sum of the array lengths to obtain a second processed array;

[0148] The vital sign data arrays of the user in the awake state, the rapid eye movement state, the light sleep state and the deep sleep state in the latter time period of the two adjacent time periods are stretched to the sum of the array lengths to obtain a third processed array.

[0149] Optionally, the data processing device 200 is further configured to:

[0150] The vital sign data arrays of the user in the awake state, the rapid eye movement state, the light sleep state and the deep sleep state in the previous time period of the two adjacent time periods are stretched to the sum of the array lengths to obtain a fourth processed array;

[0151] The data determination module 203 is specifically used for:

[0152] Based on the first processed array, the second processed array and the third processed array, a contrast loss value corresponding to the NT-Xent function is determined by a normalized temperature cross entropy NT-Xent function; and based on the first processed array, the second processed array and the fourth processed array, a contrast loss reference value corresponding to the NT-Xent function is determined by the NT-Xent function;

[0153] Based on the contrast loss value and the contrast loss reference value, it is determined whether the user vital sign data is the vital sign data of the same user to obtain the determination result.

[0154] Furthermore, an embodiment of the present application also provides an electronic device, comprising: a processor, a memory, and a system bus;

[0155] The processor and the memory are connected via the system bus;

[0156] The memory is used to store one or more programs, and the one or more programs include instructions. When the instructions are executed by the processor, the processor executes any implementation step of the above-mentioned data processing method.

[0157] Furthermore, an embodiment of the present application also provides a computer-readable storage medium, in which instructions are stored. When the instructions are executed on an electronic device, any step of the above-mentioned data processing method is implemented.

[0158] It can be known from the description of the above implementation mode that those skilled in the art can clearly understand that all or part of the steps in the above-mentioned embodiment method can be implemented by means of software plus the necessary general hardware platform. Based on such an understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product can be stored in a storage medium, such as ROM / RAM, a disk, an optical disk, etc., and includes a number of instructions for a computer device (which can be a personal computer, a server, or a network communication device such as a media gateway, etc.) to execute the methods described in each embodiment of the present application or certain parts of the embodiments. It should be noted that the various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same and similar parts between the various embodiments can be referred to each other.

[0159] As for the system disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the description of the method part.

[0160] It should also be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0161] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A data processing method, characterized in that: include: Collect user's vital sign data within a preset time period; Analyze the user's vital sign data to obtain bed rest status data within the preset time period; Determine the user's activity level based on the bed-ridden state data, and determine whether the user's vital sign data are vital sign data of the same user based on the bed-ridden state data, to obtain a determination result; The user activity ability level and the determination result are output.

2. The data processing method according to claim 1, characterized in that: The user vital sign data includes time point information indicating that the user switches between the bed-lying state and the out-of-bed state within the preset time period; The step of analyzing the user's vital sign data to obtain the bed rest status data within the preset time period includes: Analyze the time point information to determine the sum of multiple time periods during which the user is in bed within the preset time period, and the sum of time periods greater than a first time period among the multiple time periods during which the user is in bed within the preset time period, where the first time period is used to indicate a minimum duration during which the user is in bed; Determine, based on the sum of the multiple time periods and the sum of the time periods greater than the first time period, a frequency of the user switching between the lying-in-bed state and the getting-out-of-bed state within the preset time period; A sum of the multiple time periods and the frequency is determined as the bed state data.

3. The data processing method according to claim 2, characterized in that: The determining the user's activity level based on the bed status data comprises: When the sum of the multiple time periods is greater than the second duration and less than the third duration, and the frequency is greater than the first frequency and less than the second frequency, the user activity ability level is determined to be the first level; When the sum of the multiple time periods is greater than the third duration and less than the fourth duration, and the frequency is greater than the second frequency and less than the third frequency, determining the user activity level as the second level; When the sum of the multiple time periods is greater than a fourth time period and the frequency is greater than a third frequency, determining the user activity ability level as a third level; Among them, the second duration is smaller than the third duration, the third duration is smaller than the third duration, the first frequency is smaller than the second frequency, the second frequency is smaller than the third frequency, the user activity ability represented by the first level is higher than the user activity ability represented by the second level, and the user activity ability represented by the second level is higher than the user activity ability represented by the third level.

4. The data processing method according to claim 1, characterized in that: The user vital sign data includes information indicating the time point when the user switches between the bed-lying state and the out-of-bed state within the preset time period, and basic vital sign data of the user in the bed-lying state within the preset time period; The step of analyzing the user's vital sign data to obtain the bed rest status data within the preset time period includes: Analyze the time point information to determine multiple time periods during which the user is in bed within the preset time period; Determine, from the multiple time periods during which the user is in bed within the preset time period, multiple time periods greater than a fifth time period; Based on the multiple time periods greater than the fifth time period, processing the basic vital sign data of the user in the bed-resting state within the preset time period, and determining an array of vital sign data of the user in the bed-resting state within two adjacent time periods among the multiple time periods greater than the fifth time period; The vital sign data arrays of the user in the bed-resting state in the two adjacent time periods are processed to obtain a processed array, and the processed array is used as the bed-resting state data.

5. The data processing method according to claim 4, characterized in that: The step of processing the vital sign data array of the user in the bed-resting state in the two adjacent time periods to obtain a processed array includes: Determine the sum of the array lengths of the vital sign data arrays of the user in the bed-resting state in the two adjacent time periods; The array of vital sign data of the user in the bed-resting state in the two adjacent time periods is stretched to the sum of the array lengths to obtain the processed array.

6. The data processing method according to claim 5, characterized in that: The bed-lying state includes a wakeful state and a sleeping state, and the sleeping state includes a rapid eye movement state, a light sleep state, and a deep sleep state; The step of stretching the array of vital sign data of the user in the bed-resting state in the two adjacent time periods to the sum of the array lengths to obtain the processed array comprises: Lengthening the array of vital sign data of the user in the awake state in the previous time period of the two adjacent time periods to the sum of the array lengths to obtain a first processed array; Lengthening the arrays of the user's vital sign data in the rapid eye movement state, the light sleep state, and the deep sleep state in the previous time period of the two adjacent time periods to the sum of the array lengths to obtain a second processed array; The vital sign data arrays of the user in the awake state, the rapid eye movement state, the light sleep state and the deep sleep state in the latter time period of the two adjacent time periods are stretched to the sum of the array lengths to obtain a third processed array.

7. The data processing method according to claim 5, characterized in that: Before determining whether the user vital sign data is vital sign data of the same user based on the bed state data, the method further includes: The vital sign data arrays of the user in the awake state, the rapid eye movement state, the light sleep state and the deep sleep state in the previous time period of the two adjacent time periods are stretched to the sum of the array lengths to obtain a fourth processed array; The determining, based on the bed state data, whether the user vital sign data is vital sign data of the same user, and obtaining a determination result, comprises: Based on the first processed array, the second processed array and the third processed array, a contrast loss value corresponding to the NT-Xent function is determined by a normalized temperature cross entropy NT-Xent function; and based on the first processed array, the second processed array and the fourth processed array, a contrast loss reference value corresponding to the NT-Xent function is determined by the NT-Xent function; Based on the contrast loss value and the contrast loss reference value, it is determined whether the user vital sign data is the vital sign data of the same user to obtain the determination result.

8. A data processing device, characterized in that: include: A data collection module is used to collect user vital sign data within a preset time period; A data analysis module, used to analyze the user's vital sign data to obtain bed rest status data within the preset time period; a data determination module, used to determine the user's activity level based on the bed state data, and to determine whether the user's vital sign data are vital sign data of the same user based on the bed state data, to obtain a determination result; A data output module is used to output the user activity ability level and the determination result.

9. An electronic device, characterized in that: The device includes: a processor, a memory, and a system bus; The processor and the memory are connected via the system bus; The memory is used to store a program, wherein the program includes instructions, and when the instructions are executed by the processor, the processor executes the steps of the data processing method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium is used to store a computer program, and when the computer program is executed by a terminal device, the steps of the data processing method according to any one of claims 1 to 7 are implemented.

Images