An intelligent airbag pressure data analysis and management system and method based on artificial intelligence

Abstract

The present invention discloses an intelligent airbag pressure data analysis and management system and method based on artificial intelligence, which relates to the technical field of airbag pressure management, and includes analyzing the device status of intelligent airbag devices under different monitoring indicators; obtaining the medical sign data of users using intelligent airbag devices, obtaining the historical medical sign records of historical users using intelligent airbag devices, analyzing the similarity degree of medical signs between historical users and users to obtain target similar historical users; obtaining the historical pressure setting records of target similar historical users, obtaining the pressure data preset by users, analyzing the degree of fit between the pressure indicators in the pressure data and users to obtain target pressure data; controlling the airbag pressure of the intelligent airbag device used by users based on the target pressure data, and combining the target operation data to evaluate the device status of the intelligent airbag device and perform intelligent management on the intelligent airbag device.

Description

Technical Field

[0001] The present invention relates to the technical field of airbag pressure management, and in particular to an intelligent airbag pressure data analysis and management system and method based on artificial intelligence. Background Art

[0002] Currently, with the wide application of intelligent airbag devices in the medical field, the scenarios of using intelligent airbag devices are increasing. For example, when a person has traumatic blood loss, medical staff will use an intelligent airbag device, place it at the bleeding site of the person, and inflate it to increase the local pressure of the body, so as to effectively compress the peripheral blood vessels, reduce the blood flow to the wound, and thus control bleeding. At the same time, medical staff also need to accurately adjust the pressure of the intelligent airbag device to control the applied pressure and achieve the treatment of bleeding patients.

[0003] However, in real life, not only may problems occur during the use of intelligent airbag devices, but also the physical conditions of users of intelligent airbag devices vary. Different users need to set different airbag pressure data according to their actual physical conditions. Generally, this requires medical staff to set different airbag pressure data according to the actual physical conditions and needs of users for the treatment and rehabilitation of users. However, even the airbag pressure data set by professionals takes a lot of time, which not only wastes time, but may even cause further harm to the user's body due to misjudgment of the user's actual situation. Summary of the Invention

[0004] The purpose of the present invention is to provide an intelligent airbag pressure data analysis and management system and method based on artificial intelligence to solve the problems raised in the prior art.

[0005] To achieve the above purpose, the present invention provides the following technical solution: An intelligent airbag pressure data analysis and management method based on artificial intelligence, the method comprising:

[0006] Step S100: Obtain the device failure time data of the intelligent airbag device, obtain the historical device monitoring records of the intelligent airbag device, analyze the device status of the intelligent airbag device under different monitoring indicators, and obtain the target operation data;

[0007] Step S200: Obtain the medical sign data of the user using the intelligent airbag device, obtain the historical medical sign records of the historical users using the intelligent airbag device, analyze the similarity degree of medical signs between the historical users and the user, and obtain the target similar historical users;

[0008] Step S300: Obtain the historical pressure setting records of the target similar historical users, obtain the pressure data preset by the user, analyze the degree of fit between the pressure indicators in the pressure data and the user, and obtain the target pressure data;

[0009] Step S400: Based on the target pressure data, control the airbag pressure of the intelligent airbag device used by the user, and combine the target operation data to evaluate the device status of the intelligent airbag device and perform intelligent management on the intelligent airbag device.

[0010] Further, step S100 includes:

[0011] Step S101: Obtain the device failure time data of the intelligent airbag device. The device failure time data includes the historical period to which the failure of the intelligent airbag device belongs, obtain the historical device monitoring records of the intelligent airbag device, and mark the historical device monitoring records within the historical period;

[0012] Step S102: Obtain the data corresponding to the monitoring indicators of the intelligent airbag device from the historical device monitoring records;

[0013] For example, the detection indicators include device temperature, device voltage, etc.;

[0014] Step S103: Analyze the device status of the intelligent airbag device under various monitoring indicators. Among them, the specific process of analyzing the device status of the intelligent airbag device under the a-th monitoring indicator is as follows:

[0015] Obtain the preset threshold B of the a-th monitoring indicator in the intelligent airbag device a , obtain the maximum value B of the a-th monitoring indicator in a certain marked historical device monitoring record, max and the minimum value B min . When B max > B a and B min < B max , record a certain historical device monitoring record as the marked historical device monitoring record;

[0016] Step S104: Calculate the marked change amplitude C of the a-th monitoring indicator in the marked historical device monitoring record a = B a,max - B a,min / B a,△ , where B a,max is the maximum value of the a-th monitoring indicator in the marked historical device monitoring record;

[0017] Step S105: Obtain the minimum value C of the marked change amplitude of the a-th monitoring indicator in each marked historical device monitoring record of the a-th monitoring indicator a，min ;

[0018] When the minimum value C a，min is less than the preset marked change amplitude threshold C´, obtain the minimum value Ca In the corresponding marked historical device monitoring record, obtain the minimum value of the a-th monitoring index, and denote it as the target threshold of the a-th monitoring index in the intelligent airbag device;

[0019] When the minimum value C a ≥ C´, denote the threshold B a as the target threshold of the a-th monitoring index;

[0020] Step S106: Obtain the target thresholds of the monitoring indicators in the intelligent airbag device, and perform aggregation to obtain the target operation data of the intelligent airbag device.

[0021] Furthermore, step S200 includes:

[0022] Step S201: Obtain the medical sign data of the user, and from the medical sign data, obtain the medical text information input by the staff on the platform according to the user's description;

[0023] Step S202: Preprocess the medical text information, extract the keywords in the medical text information and perform aggregation to obtain the marked keyword group of the user;

[0024] Step S203: Calculate the marked word frequency of each keyword in the marked keyword group. Among them, the marked word frequency E of the d-th keyword in the marked keyword group d :

[0025] ,

[0026] where G d,sum is the d-th keyword, and the total number of times it appears in the medical text information; j is the total number of each keyword in the marked keyword group; G i,sum is the i-th keyword in the marked keyword group, and the total number of times it appears in the medical text information;

[0027] Step S204: Obtain each historical medical text information Q stored in the preset cloud platform sum , calculate the marked inverse document frequency F of the d-th keyword d :

[0028] ,

[0029] where Q d,sum is the total number of historical medical text information containing the d-th keyword;

[0030] Calculate the marked value S of the d-th keyword a = E d × F d, obtain the marking values of each keyword in the user's marked keyword group, and based on the marking values of each keyword, perform vector transformation on the marked keyword group to obtain the user's first medical sign vector W 1 ;

[0031] Step S205: Obtain the historical medical sign records of each historical user who used the intelligent airbag device within the historical period, and analyze the similarity degree between each historical user and the user. Among them, the specific process of analyzing the similarity degree between the β-th historical user and the user is as follows:

[0032] Obtain each historical medical sign record generated during the process of the β-th historical user using the intelligent airbag device, obtain the first medical sign vector of the historical user from the historical medical sign records, obtain the average value corresponding to each medical index of the β-th historical user from the historical medical sign records, and perform normalization processing on the average value corresponding to each medical index to construct the second medical sign vector of the β-th historical user in the historical medical sign records;

[0033] For example, each medical index includes weight, height, etc.;

[0034] Obtain the average value corresponding to each medical index from the user's medical sign data, and construct the second medical sign vector W of the user 2 ;

[0035] Calculate the similarity degree of medical signs between the user and the β-th historical user in each historical medical sign record. Among them, the similarity degree H of medical signs between the user and the β-th historical user in the α-th historical medical sign record β,α :

[0036] ,

[0037] where γ1 and γ2 respectively represent the preset first characteristic coefficient and second characteristic coefficient, γ1>0, γ2>0, γ1 + γ2 = 1; W 2 β,α represents the second medical sign vector of the β-th historical user in the α-th historical medical sign record; W 1 β,α represents the first medical sign vector of the β-th historical user in the α-th historical medical sign record;

[0038] Step S206: When the similarity degree of medical signs H β,α is greater than the preset similarity degree threshold, it is determined that the medical signs between the user and the β-th historical user in the α-th historical medical sign record are similar, take the α-th historical medical sign record as the user's marked historical medical sign record, and record the β-th historical user as the user's target similar historical user.

[0039] Further, step S300 includes:

[0040] Step S301: Obtain the marked historical medical feature records of each target similar historical user of the user. Based on the marked historical medical records, obtain the historical pressure setting records generated by the target similar users using the intelligent airbag device, and perform marking. From the marked historical pressure setting records, obtain the values of various pressure indicators in the intelligent airbag device;

[0041] For example, the various pressure indicators include the maximum pressure, minimum pressure, pressurization delay, pressure relief delay, etc. in the intelligent airbag device;

[0042] Step S302: Obtain the preset pressure data before the user uses the intelligent airbag device. The pressure data includes the values of various pressure indicators. Analyze the degree of fit between each pressure indicator in the pressure data and the user. Among them, the specific process of analyzing the degree of fit between the m-th pressure indicator in the pressure data and the user is as follows:

[0043] Obtain the marked historical pressure setting records of each target similar historical user. According to the time points when the historical pressure setting records are generated, sort them in chronological order, and respectively record the marked historical pressure setting records as the respective reference historical pressure setting records of the user;

[0044] Step S303: Obtain the average value K´ of the m-th pressure indicator in each reference historical pressure setting record m , calculate the characteristic value U of the m-th pressure indicator m :

[0045] ,

[0046] where n is the total number of each reference historical pressure setting record; K´ m,z is the value of the m-th pressure indicator in the z-th reference historical pressure setting record;

[0047] Obtain the characteristic range K of the m-th pressure indicator m =[K´ m -λ×U m ,K´ m +λ×U m , where λ is a preset characteristic coefficient. When the value of the m-th pressure indicator in the pressure data is not within the characteristic range, it is determined that the m-th pressure indicator in the pressure data does not fit the user, and the average value K´ m is used to replace the value of the m-th pressure indicator in the pressure data to obtain the target reference value of the m-th pressure indicator;

[0048] Conversely, it is determined that the m-th pressure index in the pressure data fits the user, and the value of the m-th pressure index in the pressure data is not processed. Instead, the value of the m-th pressure index in the pressure data is used as the target reference value for the m-th pressure index;

[0049] Step S304: Obtain the target reference values of various pressure indicators of the user on the intelligent airbag device and aggregate them to obtain the target pressure data of the user using the intelligent airbag device.

[0050] Further, step S400 includes:

[0051] Step S401: Obtain the target pressure data, set the pressure indicators of the intelligent airbag device, and control the airbag pressure of the intelligent airbag device during the user's use;

[0052] Step S402: Monitor the use of the intelligent airbag device in the current cycle and evaluate the intelligent airbag device based on the target operation data of the intelligent airbag device. The specific process is as follows:

[0053] When the value of a certain monitoring indicator in the intelligent airbag device is greater than the target threshold, it is determined that there is a risk of equipment failure in the intelligent airbag device. The intelligent airbag device is adjusted, an alarm is issued, and intelligent management of the intelligent airbag device is carried out;

[0054] In the above steps, the intelligent airbag device is set through the target pressure data. The operator does not need to have professional medical knowledge and can also achieve the reasonable use of the intelligent airbag device. Considering that the intelligent airbag device may have equipment failures during actual use, which may cause harm to the user, by evaluating the intelligent airbag device, measures are taken in advance to ensure the physical safety of the user.

[0055] To better implement the above method, an intelligent airbag pressure data analysis and management system based on artificial intelligence is also proposed. The system includes a target operation data module, a similarity analysis module, a pressure data analysis module, and an intelligent management module;

[0056] The target operation data module is used to analyze the device status of the intelligent airbag device under different monitoring indicators to obtain the target operation data;

[0057] The similarity analysis module is used to analyze the similarity of medical signs between historical users and the user to obtain the target similar historical users;

[0058] The pressure data analysis module is used to analyze the degree of fit between the pressure indicators in the pressure data and the user to obtain the target pressure data;

[0059] An intelligent management module is used to control the airbag pressure of the intelligent airbag device used by the user according to the target pressure data, and combine the target operation data to evaluate the device status of the intelligent airbag device and perform intelligent management on the intelligent airbag device.

[0060] Furthermore, the target operation data module includes a data marking unit and a target operation data unit;

[0061] The data marking unit is used to obtain the historical time period when the intelligent airbag device fails and mark the historical device monitoring records within the historical time period;

[0062] The target operation data unit is used to collect the target thresholds of various monitoring indicators in the intelligent airbag device to obtain the target operation data.

[0063] Furthermore, the similarity analysis module includes a vector construction unit and a similarity analysis unit;

[0064] The vector construction unit is used to construct the first medical sign vector and the second medical sign vector of the user;

[0065] The similarity analysis unit is used to analyze the similarity degree of medical signs between the historical user and the user according to the first medical sign vector and the second medical sign vector to obtain the target similar historical user.

[0066] Furthermore, the pressure data analysis module includes a feature range unit and a pressure data analysis unit;

[0067] The feature range unit is used to obtain the feature ranges of various pressure indicators in the user's pressure data;

[0068] The pressure data analysis unit is used to analyze the degree of fit between each pressure indicator and the user according to the feature ranges of each pressure indicator to obtain the target pressure data.

[0069] Furthermore, the intelligent management module includes an intelligent management unit;

[0070] The intelligent management unit is used to set the various pressure indicators of the intelligent airbag device, control the airbag pressure of the intelligent airbag device during the user's use process, and perform intelligent management on the intelligent airbag device.

[0071] Compared with the prior art, the beneficial effects of the present invention are as follows: By intelligently analyzing the airbag pressure data in the intelligent airbag device, the present invention realizes the intelligent management of the intelligent airbag device. Considering the practical problem that during the treatment of patients with the intelligent airbag device, it is necessary to manually set the pressure index of the intelligent airbag device, through the analysis of the characteristics of the users of the device and the historical data of the intelligent airbag device, the target pressure data is obtained, so that personnel without professional knowledge can also use the intelligent airbag device to treat users. BRIEF DESCRIPTION OF THE DRAWINGS

[0072] Figure 1 is a method flowchart of a method for analyzing and managing intelligent airbag pressure data based on artificial intelligence according to the present invention;

[0073] Figure 2 is a module schematic diagram of a system for analyzing and managing intelligent airbag pressure data based on artificial intelligence according to the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0074] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0075] Embodiment: As Figure 1 - Figure 2 shown, the present invention provides a technical solution, a method for analyzing and managing intelligent airbag pressure data based on artificial intelligence, the method comprising:

[0076] Step S100: Obtain the device failure time data of the intelligent airbag device, obtain the historical device monitoring records of the intelligent airbag device, analyze the device status of the intelligent airbag device under different monitoring indicators, and obtain the target operation data;

[0077] Among them, step S100 includes:

[0078] Step S101: Obtain the device failure time data of the intelligent airbag device. The device failure time data includes the historical time period to which the failure of the intelligent airbag device belongs, obtain the historical device monitoring records of the intelligent airbag device, and mark the historical device monitoring records within the historical time period;

[0079] Step S102: Obtain the data corresponding to each monitoring indicator of the intelligent airbag device from the historical device monitoring records;

[0080] Step S103: Analyze the device status of the intelligent airbag device under various monitoring indicators. Among them, the specific process of analyzing the device status of the intelligent airbag device under the a-th monitoring indicator is as follows:

[0081] Obtain the preset threshold B of the a-th monitoring indicator in the intelligent airbag device a , obtain the maximum value B of the a-th monitoring indicator in a certain marked historical device monitoring record max and the minimum value B min . When B max >B a and B min <B max , mark a certain historical device monitoring record as the marked historical device monitoring record;

[0082] Step S104: Calculate the marked change amplitude C of the a-th monitoring indicator in the marked historical device monitoring record a =B a,max -B a,min / B a,△ , where B a,max is the maximum value of the a-th monitoring indicator in the marked historical device monitoring record;

[0083] Step S105: Obtain the minimum value C of the marked change amplitude of the a-th monitoring indicator in each marked historical device monitoring record of the a-th monitoring indicator a，min ;

[0084] When the minimum value C a，min is less than the preset marked change amplitude threshold C´, obtain the minimum value of the a-th monitoring indicator in the marked historical device monitoring record corresponding to the minimum value C a , and record it as the target threshold of the a-th monitoring indicator in the intelligent airbag device;

[0085] When the minimum value C a ≥C´, record the threshold B a as the target threshold of the a-th monitoring indicator;

[0086] Step S106: Obtain the target thresholds of each monitoring indicator in the intelligent airbag device and aggregate them to obtain the target operation data of the intelligent airbag device;

[0087] Step S200: Obtain the medical sign data of the user using the intelligent airbag device, obtain the historical medical sign records of the historical users using the intelligent airbag device, analyze the similarity degree of the medical signs between the historical users and the user, and obtain the target similar historical users;

[0088] Among them, Step S200 includes:

[0089] Step S201: Obtain the user's medical sign data, and from the medical sign data, obtain the medical text information input by the staff on the platform according to the user's description;

[0090] Step S202: Preprocess the medical text information, extract the keywords in the medical text information and pool them to obtain the user's marked keyword group;

[0091] Step S203: Calculate the marked word frequency of each keyword in the marked keyword group. Among them, the marked word frequency E of the d-th keyword in the marked keyword group d :

[0092] ,

[0093] where G d,sum is the d-th keyword, and the total number of times it appears in the medical text information; j is the total number of each keyword in the marked keyword group; G i,sum is the i-th keyword in the marked keyword group, and the total number of times it appears in the medical text information;

[0094] For example, j is 5; G 1,sum is 20; G 2,sum is 13; G 3,sum is 15; G 4,sum is 20; G 5,sum is 17; Calculate the marked word frequency E1 of the first keyword in the marked keyword group:

[0095] ,

[0096] Step S204: Obtain each historical medical text information Q stored in the preset cloud platform sum , calculate the marked inverse document frequency F of the d-th keyword d :

[0097] ,

[0098] where Q d,sum is the total number of historical medical text information containing the d-th keyword;

[0099] Calculate the marked value S of the d-th keyword a =E d ×F d , obtain the marked values of each keyword in the user's marked keyword group, and based on the marked values of each keyword, perform vector transformation on the marked keyword group to obtain the user's first medical sign vector W 1 ;

[0100] Step S205: Obtain the historical medical sign records of each historical user who used the intelligent airbag device during the historical period, and analyze the similarity degree between each historical user and the user. Among them, the specific process of analyzing the similarity degree between the β-th historical user and the user is as follows:

[0101] Obtain each historical medical sign record generated during the process of the β-th historical user using the intelligent airbag device, obtain the first medical sign vector of the historical user from the historical medical sign records, obtain the average value corresponding to each medical index of the β-th historical user from the historical medical sign records, and perform normalization processing on the average value corresponding to each medical index to construct the second medical sign vector of the β-th historical user in the historical medical sign records;

[0102] Obtain the average value corresponding to each medical index from the user's medical sign data, and construct the second medical sign vector W of the user 2 ;

[0103] Calculate the similarity degree of medical signs between the user and the β-th historical user in each historical medical sign record. Among them, the similarity degree H of medical signs between the user and the β-th historical user in the α-th historical medical sign record β,α :

[0104] ,

[0105] where γ1 and γ2 respectively represent the preset first feature coefficient and second feature coefficient, γ1>0, γ2>0, and γ1 + γ2 = 1; W 2 β,α represents the second medical sign vector of the β-th historical user in the α-th historical medical sign record; W 1 β,α represents the first medical sign vector of the β-th historical user in the α-th historical medical sign record;

[0106] Step S206: When the similarity degree H of medical signs β,α is greater than the preset similarity degree threshold, it is determined that the medical signs between the user and the β-th historical user in the α-th historical medical sign record are similar. The α-th historical medical sign record is used as the marked historical medical sign record of the user, and the β-th historical user is recorded as the target similar historical user of the user;

[0107] Step S300: Obtain the historical pressure setting records of the target similar historical user, obtain the pressure data preset by the user, analyze the degree of fit between the pressure index in the pressure data and the user, and obtain the target pressure data;

[0108] Among them, Step S300 includes:

[0109] Step S301: Obtain the marked historical medical feature records of each target similar historical user of the user. Based on the marked historical medical records, obtain the historical pressure setting records generated by the target similar users using the intelligent airbag device, and mark them. From the marked historical pressure setting records, obtain the values of each pressure index in the intelligent airbag device;

[0110] Step S302: Obtain the preset pressure data before the user uses the intelligent airbag device. The pressure data includes the values of each pressure index. Analyze the degree of fit between each pressure index in the pressure data and the user. Among them, the specific process of analyzing the degree of fit between the m-th pressure index in the pressure data and the user is as follows:

[0111] Obtain each marked historical pressure setting record among each target similar historical user. According to the time points when the historical pressure setting records are generated, sort them in chronological order, and respectively record each marked historical pressure setting record as each reference historical pressure setting record of the user;

[0112] Step S303: Obtain the average value K' of the m-th pressure index in each reference historical pressure setting record m , calculate the eigenvalue U of the m-th pressure index m :

[0113] ,

[0114] where n is the total number of each reference historical pressure setting record; K' m,z is the value of the m-th pressure index in the z-th reference historical pressure setting record;

[0115] Obtain the characteristic range K of the m-th pressure index m =[K' m -λ×U m ,K' m +λ×U m , where λ is a preset characteristic coefficient. When the value of the m-th pressure index in the pressure data is not within the characteristic range, it is determined that the m-th pressure index in the pressure data does not fit the user, and the average value K' m is used to replace the value of the m-th pressure index in the pressure data to obtain the target reference value of the m-th pressure index;

[0116] On the contrary, it is determined that the m-th pressure index in the pressure data fits the user, and the value of the m-th pressure index in the pressure data is not processed, and the value of the m-th pressure index in the pressure data is used as the target reference value of the m-th pressure index;

[0117] Step S304: Obtain the target reference values of various pressure indicators on the intelligent airbag device and aggregate them to obtain the target pressure data for the user's use of the intelligent airbag device;

[0118] Step S400: Based on the target pressure data, control the airbag pressure of the intelligent airbag device used by the user, and combine the target operation data to evaluate the device status of the intelligent airbag device and perform intelligent management on the intelligent airbag device;

[0119] Among them, Step S400 includes:

[0120] Step S401: Obtain the target pressure data, set various pressure indicators of the intelligent airbag device, and control the airbag pressure of the intelligent airbag device during the user's use;

[0121] Step S402: Monitor the use of the intelligent airbag device in the current cycle, and evaluate the intelligent airbag device based on the target operation data of the intelligent airbag device. The specific process is as follows:

[0122] When the value of a certain monitoring indicator in the intelligent airbag device is greater than the target threshold, it is determined that there is a risk of device failure in the intelligent airbag device, adjust the intelligent airbag device, issue an alarm, and perform intelligent management on the intelligent airbag device;

[0123] In order to better implement the above method, an intelligent airbag pressure data analysis and management system based on artificial intelligence is also proposed. The system includes a target operation data module, a similarity analysis module, a pressure data analysis module, and an intelligent management module;

[0124] The target operation data module is used to analyze the device status of the intelligent airbag device under different monitoring indicators to obtain the target operation data;

[0125] The similarity analysis module is used to analyze the similarity of medical signs between historical users and the user to obtain the target similar historical users;

[0126] The pressure data analysis module is used to analyze the degree of fit between the pressure indicators in the pressure data and the user to obtain the target pressure data;

[0127] The intelligent management module is used to control the airbag pressure of the intelligent airbag device used by the user according to the target pressure data, and combine the target operation data to evaluate the device status of the intelligent airbag device and perform intelligent management on the intelligent airbag device;

[0128] Among them, the target operation data module includes a data marking unit and a target operation data unit;

[0129] A data marking unit for obtaining the historical periods when the intelligent airbag device fails and marking the historical device monitoring records within the historical periods;

[0130] A target operation data unit for collecting the target thresholds of various monitoring indicators in the intelligent airbag device to obtain target operation data;

[0131] Among them, the similarity analysis module includes a vector construction unit and a similarity analysis unit;

[0132] The vector construction unit is used to construct the first medical sign vector and the second medical sign vector of the user;

[0133] The similarity analysis unit is used to analyze the similarity degree of medical signs between the historical user and the user according to the first medical sign vector and the second medical sign vector to obtain the target similar historical user;

[0134] Among them, the pressure data analysis module includes a feature range unit and a pressure data analysis unit;

[0135] The feature range unit is used to obtain the feature ranges of various pressure indicators in the user's pressure data;

[0136] The pressure data analysis unit is used to analyze the degree of fit between each pressure indicator and the user according to the feature ranges of each pressure indicator to obtain the target pressure data;

[0137] Among them, the intelligent management module includes an intelligent management unit;

[0138] The intelligent management unit is used to set the various pressure indicators of the intelligent airbag device and control the airbag pressure of the intelligent airbag device during the user's use process to perform intelligent management on the intelligent airbag device.

[0139] For those skilled in the art, it is obvious that the present invention is not limited to the details of the above exemplary embodiments, and without departing from the spirit or basic characteristics of the present invention, the present invention can be implemented in other specific forms. Therefore, from any point of view, the embodiments should be regarded as exemplary and non-limiting. The scope of the present invention is defined by the appended claims rather than the above description. Therefore, it is intended to encompass all changes falling within the meaning and scope of the equivalent elements of the claims in the present invention. Any reference signs in the claims should not be regarded as limiting the claimed rights.

Claims

1. An intelligent airbag pressure data analysis and management method based on artificial intelligence, characterized in that, The method includes: Step S100: Obtain the device failure time data of the intelligent airbag device, obtain the historical device monitoring records of the intelligent airbag device, analyze the device conditions of the intelligent airbag device under different monitoring indicators, and obtain the target operation data; Step S200: Obtain the medical sign data of the user using the intelligent airbag device, obtain the historical medical sign records of the historical users using the intelligent airbag device, analyze the similarity degree of the medical signs between the historical users and the user, and obtain the target similar historical users; Step S300: Obtain the historical pressure setting records of the target similar historical users, obtain the pressure data preset by the user, analyze the degree of fit between the pressure indicators in the pressure data and the user, and obtain the target pressure data; Step S400: Based on the target pressure data, control the airbag pressure of the intelligent airbag device used by the user, and combine the target operation data to evaluate the device state of the intelligent airbag device and perform intelligent management on the intelligent airbag device; The step S100 includes: Step S101: Obtain the device failure time data of the intelligent airbag device. The device failure time data includes the historical time period when the intelligent airbag device fails. Obtain the historical device monitoring records of the intelligent airbag device and mark the historical device monitoring records within the historical time period; Step S102: Obtain the data corresponding to each monitoring indicator of the intelligent airbag device from the historical device monitoring records; Step S103: Analyze the device conditions of the intelligent airbag device under each monitoring indicator. Among them, the specific process of analyzing the device conditions of the intelligent airbag device under the a-th monitoring indicator is: Obtain the preset threshold B for the a-th monitoring index in the intelligent airbag device a , and obtain the maximum value B of the a-th monitoring index in a certain marked historical device monitoring record max and the minimum value B min . When B max > B a and B min < B max , record the certain historical device monitoring record as the marked historical device monitoring record Step S104: Calculate the marker change amplitude C of the ath monitoring index in the marker history device monitoring record a =B a,max -B a,min / B a,△ , where B a,max is the maximum value of the ath monitoring index in the marker history device monitoring record; Step S105: Obtain the minimum value C of the marked change range of the a-th monitoring index in the respective marked historical device monitoring records of the a-th monitoring index a，min ; When the minimum value C a，min is less than a preset marker change amplitude threshold C´, obtain the minimum value C a of the a-th monitoring index in the marker history device monitoring record corresponding to it, and record it as the target threshold of the a-th monitoring index in the intelligent airbag device; When the minimum value C a ≥ C´, the threshold B a is recorded as the target threshold of the a-th monitoring index; Step S106: Obtain the target thresholds of each monitoring indicator in the intelligent airbag device and aggregate them to obtain the target operation data of the intelligent airbag device.

2. The intelligent airbag pressure data analysis and management method based on artificial intelligence according to claim 1, characterized in that, The step S200 includes: Step S201: Obtain the medical sign data of the user, and obtain the medical text information input by the staff on the platform according to the description of the user from the medical sign data; Step S202: Perform preprocessing on the medical text information, extract the keywords in the medical text information and aggregate them to obtain the marked keyword group of the user; Step S203: Calculate the marked word frequencies of the respective keywords in the marked keyword group, where the marked word frequency E of the d-th keyword in the marked keyword group d : ， where G d,sum is the total number of times that the d-th keyword appears in the medical text information; j is the total number of each keyword in the marked keyword group; G i,sum is the total number of times that the i-th keyword in the marked keyword group appears in the medical text information; Step S204: Obtain each piece of historical medical text information Q stored in a preset cloud platform sum , and calculate the term inverse document frequency F of the d-th keyword d : ， Among them, Q d,sum is the total number of historical medical text information containing the d-th keyword; Calculate the tag value S of the d-th keyword a =E d ×F d , obtain the tag values of each keyword in the tagged keyword group of the user, and based on the tag values of each keyword, perform vector transformation on the tagged keyword group to obtain the first medical sign vector W of the user 1 ; Step S205: Obtain the historical medical sign records of each historical user who used the intelligent airbag device within the historical period, and analyze the similarity degree between each historical user and the user. Among them, the specific process of analyzing the similarity degree between the β-th historical user and the user is: Obtain each historical medical sign record generated during the process of the β-th historical user using the intelligent airbag device, obtain the first medical sign vector of the historical user from the historical medical sign records, obtain the average value corresponding to each medical index of the β-th historical user from the historical medical sign records, and perform normalization processing on the average value corresponding to each medical index to construct the second medical sign vector of the β-th historical user in the historical medical sign records; Obtain the average value corresponding to each medical index from the medical sign data of the user, and construct a second medical sign vector W of the user 2 ; Calculate the similarity degree of medical signs between the user and the β-th historical user among the respective historical medical sign records, where the similarity degree H of medical signs between the user and the β-th historical user in the α-th historical medical sign record β,α : ， where γ1 and γ2 are respectively the preset first and second characteristic coefficients, γ1 > 0, γ2 > 0, and γ1 + γ2 = 1; W 2 β,α represents the second medical sign vector of the β-th historical user in the α-th historical medical sign record; W 1 β,α represents the first medical sign vector of the β-th historical user in the α-th historical medical sign record; Step S206: When the similarity degree H of the medical signs β,α is greater than a preset similarity degree threshold, it is determined that the medical signs of the user are similar to those of the β-th historical user in the α-th historical medical sign record. The α-th historical medical sign record is used as the marked historical medical sign record of the user, and the β-th historical user is recorded as the target similar historical user of the user.

3. The intelligent airbag pressure data analysis and management method based on artificial intelligence according to claim 2, wherein, The step S300 includes: Step S301: Obtain the marked historical medical feature records of each target similar historical user of the user, based on the marked historical medical records, obtain the historical pressure setting records generated by the target similar users using the intelligent airbag device, and perform marking. From the marked historical pressure setting records, obtain the values of each pressure index in the intelligent airbag device; Step S302: Obtain the preset pressure data before the user uses the intelligent airbag device. The pressure data includes the values of each pressure index. Analyze the degree of fit between each pressure index in the pressure data and the user. Among them, the specific process of analyzing the degree of fit between the m-th pressure index in the pressure data and the user is: Obtain each marked historical pressure setting record among each target similar historical user, sort them in chronological order according to the time points when the historical pressure setting records are generated, and respectively record each marked historical pressure setting record as each reference historical pressure setting record of the user; Step S303: Obtain the average value K' of the m-th pressure index in each of the reference historical pressure setting records, and calculate the eigenvalue U of the m-th pressure index m , and calculate the eigenvalue U of the m-th pressure index m :[[]]END]] ， where n is the total number of the respective reference historical pressure setting records; K´ m,z is the value of the m-th pressure index in the z-th reference historical pressure setting record; Obtain the characteristic range K of the m-th pressure index m =[K´ m -λ×U m ,K´ m +λ×U m , where λ is a preset characteristic coefficient. When the value of the m-th pressure index in the pressure data is not within the characteristic range, it is determined that the m-th pressure index in the pressure data does not match the user, and the average value K´ m is used to replace the value of the m-th pressure index in the pressure data to obtain the target reference value of the m-th pressure index; On the contrary, determine that the m-th pressure index in the pressure data fits the user, and do not process the value of the m-th pressure index in the pressure data, and use the value of the m-th pressure index in the pressure data as the target reference value of the m-th pressure index; Step S304: Obtain the target reference values of each pressure index of the user on the intelligent airbag device, and perform aggregation to obtain the target pressure data for the user to use the intelligent airbag device.

4. The intelligent airbag pressure data analysis and management method based on artificial intelligence according to claim 3, wherein, The step S400 includes: Step S401: Obtain the target pressure data, set each pressure index of the intelligent airbag device, and control the airbag pressure of the intelligent airbag device during the user's use process; Step S402: Monitor the use of the intelligent airbag device in the current cycle, and evaluate the intelligent airbag device based on the target operation data of the intelligent airbag device. The specific process is: When the value of a certain monitoring index in the intelligent airbag device is greater than the target threshold, determine that there is a risk of equipment failure in the intelligent airbag device, adjust the intelligent airbag device, issue an alarm, and perform intelligent management on the intelligent airbag device.

5. An intelligent airbag pressure data analysis and management system based on artificial intelligence, which is used to execute an intelligent airbag pressure data analysis and management method according to any one of claims 1-4, characterized in that, The system includes a target operation data module, a similarity analysis module, a pressure data analysis module, and an intelligent management module; The target operation data module is used to analyze the device status of the intelligent airbag device under different monitoring indexes to obtain target operation data; The similarity analysis module is used to analyze the similarity degree of medical signs between the historical user and the user, and obtain the target similar historical user; The pressure data analysis module is used to analyze the degree of fit between the pressure indicators in the pressure data and the user, and obtain the target pressure data; The intelligent management module is used to control the airbag pressure of the intelligent airbag device used by the user according to the target pressure data, and evaluate the device state of the intelligent airbag device in combination with the target operation data, and perform intelligent management on the intelligent airbag device.

6. The intelligent airbag pressure data analysis and management system based on artificial intelligence according to claim 5, characterized in that, The target operation data module includes a data marking unit and a target operation data unit; The data marking unit is used to obtain the historical time period when the intelligent airbag device fails, and mark the historical device monitoring records during the historical time period; The target operation data unit is used to collect the target thresholds of various monitoring indicators in the intelligent airbag device to obtain the target operation data.

7. An intelligent airbag pressure data analysis and management system based on artificial intelligence according to claim 5, characterized in that, The similarity analysis module includes a vector construction unit and a similarity analysis unit; The vector construction unit is used to construct the first medical sign vector and the second medical sign vector of the user; The similarity analysis unit is used to analyze the similarity degree of medical signs between the historical user and the user according to the first medical sign vector and the second medical sign vector, and obtain the target similar historical user.

8. An intelligent airbag pressure data analysis and management system based on artificial intelligence according to claim 5, characterized in that, The pressure data analysis module includes a feature range unit and a pressure data analysis unit; The feature range unit is used to obtain the feature ranges of various pressure indicators in the pressure data of the user; The pressure data analysis unit is used to analyze the degree of fit between the various pressure indicators and the user according to the feature ranges of the various pressure indicators, and obtain the target pressure data.

9. An intelligent airbag pressure data analysis and management system based on artificial intelligence according to claim 5, characterized in that, The intelligent management module includes an intelligent management unit; The intelligent management unit is used to set the various pressure indicators of the intelligent airbag device, and control the airbag pressure of the intelligent airbag device during the use of the user, and perform intelligent management on the intelligent airbag device.

Images