A maternity patient needs confirmation system

Abstract

The present application provides a maternal demand confirmation system, which relates to the field of data processing. The system includes: an information collection robot and an information prompt module. Among them, the information collection robot includes an information collection unit, an information analysis unit, and an information sending unit. The information collection unit is used to interact with the target pregnant woman to obtain a list of output information of the target pregnant woman. The information analysis unit is used to obtain a list of target output words according to the list of output information. The information sending unit is used to send the list of target output words to the information prompt module. The information prompt module is used to display each target output word in the list of target output words. The present application can enable relevant medical staff to pay attention to some maternal conditions that may be overlooked based on the above-mentioned words worthy of attention, so as to ensure that the physical health indicators of each pregnant woman in the entire pregnancy cycle are effectively monitored and timely adjusted.

Description

Background Art

[0002] Regular prenatal check-ups for pregnant women are an essential and crucial link in ensuring the health of both the mother and the baby. Although current technology has developed to the point of using intelligent robots to assist in collecting basic information about pregnant women, this innovative approach, while bringing convenience to the medical process, still has certain limitations in deeply understanding and accurately extracting key concerns in the content of pregnant women's self-reported statements to assist doctors in making diagnoses.

[0003] Since the specific physical index situations of each pregnant woman are different, how to collect effective content from the interaction between pregnant women and robots has become an urgent problem to be solved. Summary of the Invention

[0004] In view of the above technical problems, the present application provides a pregnant woman's demand confirmation system, which at least partially solves the problems existing in the prior art.

[0005] In a first aspect of the present application, there is provided a pregnant woman's demand confirmation system, the system comprising: an information collection robot and an information prompt module; wherein, the information collection robot comprises an information collection unit, an information analysis unit, and an information sending unit;

[0006] The information collection unit of the information collection robot is used to interact with a target pregnant woman to obtain a list of output information of the target pregnant woman;

[0007] The information analysis unit of the information collection robot is used to obtain a list of target output words according to the list of output information; wherein, the list of target output words comprises a first sub-list of target output words and a second sub-list of target output words; the occurrence frequency of each first target output word in the first sub-list of target output words is equal to or greater than a preset frequency threshold; the occurrence frequency of each second target output word in the second sub-list of target output words is less than the preset frequency threshold, and each second target output word is the same as any preset concern word; the preset concern words are the concern words corresponding to a number of historical abnormal pregnant women;

[0008] The information sending unit of the information collection robot is used to send the list of target output words to the information prompt module;

[0009] The information prompt module is used to display each target output word in the list of target output words.

[0010] The present application has at least the following beneficial effects:

[0011] The maternal demand confirmation system provided by this application includes an information collection robot and an information prompt module. The information collection robot includes an information collection unit, an information analysis unit, and an information sending unit. First, before the current prenatal examination, the information collection unit interacts with the target pregnant woman through voice, text, etc. to obtain the output information list of the target pregnant woman, that is, to obtain all the outputs of the target pregnant woman. Then, according to the output information list, the target output word list is obtained. Here, after each output information in the output information list is segmented, the words with higher occurrence frequencies and the words with lower occurrence frequencies but the same as the attention words corresponding to historical abnormal pregnant women are output to the corresponding medical staff. Here, the words with higher occurrence frequencies (the first target output words) are the words repeatedly mentioned by the target pregnant woman during the interaction with the information collection robot, which may represent some problems that the target pregnant woman is confused about, or the corresponding physical abnormal conditions, and need to be highlighted to the corresponding medical staff to assist the doctor in making a diagnosis. For the words with lower occurrence frequencies but the same as the attention words corresponding to historical abnormal pregnant women, because the cultural background, educational background, and understanding of medical knowledge of each pregnant woman are different, some words corresponding to physical conditions or other related matters may be ignored by them. Therefore, there may also be some words that need to be highlighted to the doctor among the words not mentioned many times. According to the relevant attention words corresponding to historical abnormal pregnant women as a reference, the same second target output words are output. In this way, the words worthy of attention during the interaction between the target pregnant woman and the information collection robot are collected, so as to assist the relevant medical staff to determine the prenatal examination content and issue medical orders according to the above-mentioned words worthy of attention, and enable the relevant medical staff to pay attention to some pregnant woman situations that may be ignored according to the above-mentioned words worthy of attention, so as to ensure that the physical health indicators of each pregnant woman during the entire pregnancy cycle are effectively monitored and timely adjusted. In addition, it is also possible to learn some of the pregnant woman's needs according to the above-mentioned words worthy of attention, so as to solve the pregnant woman's doubts within the limited consultation time and avoid missing some inquiry content during the consultation. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] In order to more clearly illustrate the technical solutions in the embodiments of this application, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of this application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained according to these drawings.

[0013] Figure 1 It is a structural block diagram of the maternal demand confirmation system provided by the embodiment of this application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0014] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative efforts belong to the scope of protection of the present application.

[0015] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and do not have to be used to describe a specific order or sequence. It should be understood that such used data may be interchanged under appropriate circumstances so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or server including a series of steps or units does not have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0016] It should be noted that various aspects of the embodiments within the scope of the appended claims are described below. It should be apparent that the aspects described herein can be embodied in a wide variety of forms, and any specific structure and / or function described herein is illustrative only. Based on the present application, those skilled in the art should understand that one aspect described herein can be implemented independently of any other aspect, and two or more of these aspects can be combined in various ways. For example, any number of aspects described herein can be used to implement a device and / or practice a method. Additionally, this device and / or this method can be implemented using other structures and / or functions in addition to one or more of the aspects described herein.

[0017] Please refer to Figure 1 As shown, an embodiment of the present application provides a maternity demand confirmation system 100, and the system includes: an information collection robot 110 and an information prompt module 120; wherein, the information collection robot includes an information collection unit 111, an information analysis unit 112, and an information sending unit 113;

[0018] The information collection unit 111 of the information collection robot 110 is used to interact with the target pregnant woman to obtain a list of output information of the target pregnant woman.

[0019] Specifically, the output information list includes identity information, historical medical order cooperation information, and user personalization information. The interaction methods include voice interaction, text interaction, etc. The identity information of the target pregnant woman can be obtained through various methods such as manual input, face scanning input, and ID card swiping input. In one embodiment, the historical medical order cooperation information is the self-report of the target pregnant woman on the execution status of each medical order item in the most recent historical medical order as of the current time obtained by the information collection unit 111 of the information collection robot 110 through interaction with the target pregnant woman. The user personalization information can be information such as the speaking speed, common words, and speaking attitude of the target pregnant woman obtained by the target robot through interaction with the target pregnant woman using a number of preset questions.

[0020] The information analysis unit 112 of the information collection robot 110 is used to obtain a target output word list according to the output information list; wherein, the target output word list includes a first target output word sub-list and a second target output word sub-list; the occurrence frequency of each first target output word in the first target output word sub-list is equal to or greater than a preset frequency threshold; the occurrence frequency of each second target output word in the second target output word sub-list is less than the preset frequency threshold, and each second target output word is the same as any preset attention word; the preset attention word is the attention word corresponding to a number of historical abnormal pregnant women.

[0021] Specifically, the information analysis unit is used to perform the following steps to obtain the first target output word sub-list:

[0022] S210, perform word segmentation on each output information in the output information list to obtain a number of initial words.

[0023] Among them, according to the preset word segmentation method, perform word segmentation on each output information in the output information list to obtain a number of initial words. Among them, each output information is a natural sentence.

[0024] S220, obtain a number of intermediate words according to the preset keyword library; wherein, the intermediate words are the initial words that are the same as any keyword in the preset keyword library.

[0025] The preset keyword library stores a number of keywords corresponding to pregnant and lying-in women; as an example: abdominal pain, amniotic fluid, fetal movement, etc. The purpose of this step is to filter out the words in the initial words that have nothing to do with pregnant and lying-in women, such as: you, me, evening and other irrelevant words.

[0026] S230, obtain the first target output word sub-list YL=(YL 1 ,YL 2 ,…,YL j, …, YL m ); j = 1, 2, …, m; where m is the number of the first target output words; YL j is the j-th first target output word; YL j The occurrence frequency in the output information list is equal to or greater than a preset frequency threshold.

[0027] Determine each intermediate word whose occurrence frequency in the output information list is equal to or greater than the preset frequency threshold as the first target output word.

[0028] In this embodiment, first, filter out the words irrelevant to the pregnant and lying-in women to avoid noise interference. Secondly, determine the words with a higher occurrence frequency, that is, the words repeatedly mentioned by the target parturient during the interaction with the information collection robot, as the first target output words. The first target output words may represent some questions that the target parturient is puzzled about, or the corresponding physical abnormalities, which need to be highlighted to the doctor to assist the doctor in making a diagnosis.

[0029] After step S220, the information analysis unit is used to perform the following steps to obtain the second target output word sub-list:

[0030] S240, obtain a number of temporary words according to a number of intermediate words and a preset frequency threshold; where the temporary words are intermediate words whose occurrence frequency in the output information list is less than the preset frequency threshold.

[0031] S250, obtain the corresponding second target output word sub-list EL = (EL 1 , EL 2 , …, EL p , …, EL q ); p = 1, 2, …, q; where q is the number of the second target output words; EL p is the p-th second target output word.

[0032] Among them, after screening out the first target output word sub-list, the occurrence frequency of each remaining intermediate word (i.e., each temporary word) in the output information list is less than the preset frequency threshold. However, due to the different cultural backgrounds, educational backgrounds and understanding of medical knowledge of each pregnant and lying-in woman, some words corresponding to physical conditions or other related matters may be ignored by her. Therefore, there may also be some words that need to be highlighted to the doctor among the several temporary words.

[0033] In addition, each historical abnormal parturient has a corresponding abnormal parturient portrait; the historical abnormal parturient refers to a parturient whose at least one physical health index is abnormal within a historical time period. The abnormal parturient portrait is the user portrait corresponding to the abnormal parturient, including the historical antenatal examination results corresponding to each historical abnormal parturient, and the descriptive words mapped from the abnormal indicators and normal indicators included therein; as an example: if the weight in the historical antenatal examination results is much higher, the descriptive word that may be mapped is obesity, and obesity is one of the descriptive words in the abnormal parturient portrait corresponding to this historical abnormal parturient. Furthermore, each abnormal parturient portrait is encoded according to the one-hot encoding method to obtain a corresponding abnormal feature vector.

[0034] The preset determination method includes:

[0035] S251, clustering according to the abnormal parturient portraits corresponding to each historical abnormal parturient among a number of historical abnormal parturients to obtain a corresponding clustering cluster list J=(J 1 , J 2 , …, J x , …, J y ); x = 1, 2, …, y; y is the number of clustering clusters; J x is the cluster identifier corresponding to the x-th clustering cluster; each clustering cluster includes at least one abnormal parturient portrait; each abnormal parturient portrait has a corresponding abnormal feature vector; each historical abnormal parturient has a corresponding preset attention word list; each clustering cluster has a corresponding preset attention word list set.

[0036] Among them, the matching degree between the abnormal feature vectors corresponding to the abnormal parturient portraits of any two historical abnormal parturients within each clustering cluster is less than a preset abnormal matching degree threshold. That is, each clustering cluster represents a category of historical abnormal parturients. The abnormal situations among the historical abnormal parturients within the same clustering cluster are similar.

[0037] In addition, each historical abnormal parturient has a corresponding preset attention word list, and each preset attention word in this preset attention word list is a descriptive word mapped from the abnormal situation in the historical antenatal examination results corresponding to this historical abnormal parturient. As an example: the preset attention words may be obesity, pregnancy-induced hypertension, etc.

[0038] S252, obtaining a clustering cluster center vector list ZJ=(ZJ 1 , ZJ 2 , …, ZJ x , …, ZJ y ) according to the abnormal feature vectors corresponding to each abnormal parturient portrait included in each clustering cluster; among them, ZJ x is the center vector corresponding to J x .

[0039] Here, according to the abnormal feature vectors corresponding to all the abnormal parturient portraits included in each cluster, the central vector corresponding to each cluster is obtained, and this central vector can be the average vector of each cluster.

[0040] S253. Obtain the target feature vector MT of the target portrait corresponding to the target parturient.

[0041] Obtain the target portrait corresponding to the target parturient, and encode it according to the one-hot encoding method to obtain MT.

[0042] S254. According to MT and ZJ, obtain the key matching degree list MJ = (MJ 1 , MJ 2 , …, MJ x , …, MJ y ); where MJ x is the matching degree between MT and ZJ x . Obtain the target portrait corresponding to the target parturient, and encode it according to the one-hot encoding method to obtain MT. MJ x meets the following conditions:

[0043] MJ x = (MT·ZJ x ) / (|MT| × |ZJ x |).

[0044] S255. If MJ x is greater than the preset matching degree threshold, then determine J x as the target cluster.

[0045] S256. Determine any temporary word that is the same as a preset attention word in the preset attention word list set corresponding to J x as the second target output word, so as to obtain the second target output word sub-list EL.

[0046] Here, the larger MJ x is, the more similar the target portrait is to a class of historical parturient portraits corresponding to J x , and the overall situation of the historical prenatal examination results corresponding to the target parturient may be similar to the situation of a class of historical abnormal parturients corresponding to J x . That is, the target parturient may have the same abnormal problems as a class of historical abnormal parturients corresponding to J x . Therefore, if a certain temporary word (that is, a word with a low frequency of occurrence, that is, a word mentioned by the target parturient but not frequently mentioned) is the same as any preset attention word in the preset attention word list set corresponding to J x , it means that it may be a signal of potential risks for the target parturient and needs to be focused on, so it is used as the second target output word.

[0047] In an exemplary embodiment of the present application, each keyword in the preset keyword library has a corresponding importance score;

[0048] After step S230, the information analysis unit is further configured to perform the following steps:

[0049] S260. Obtain the corresponding arrangement priority XL=(XL 1 , XL 2 , …, XL j , …, XL m ) according to the importance score and the occurrence frequency of the keyword corresponding to each first target output word; wherein, XL j is the corresponding arrangement priority of YL j ; XL j meets the following conditions:

[0050] XL j =YD j *XP j

[0051] wherein, YD j is the importance score of the keyword corresponding to YL j ; XP j is the occurrence frequency of the keyword corresponding to YL j in the output information list.

[0052] Specifically, each keyword in the preset keyword library is provided with a corresponding importance score according to its importance. As an example: the importance score of amniotic fluid is 0.8; the importance score of low back pain is 0.3.

[0053] In this embodiment, according to the importance score and the occurrence frequency of the keyword corresponding to each first target output word, obtain the corresponding arrangement priority of each first target output word, that is, when displaying each first target output word, give priority to displaying the first target output word with a higher arrangement priority, so as to remind the doctor in time according to the importance of each first target output word.

[0054] In an exemplary embodiment of the present application, the information collection robot further includes an information preprocessing unit, and the information and processing unit is configured to perform the following steps:

[0055] Perform word standardization conversion processing on a number of initial words.

[0056] Specifically, after obtaining a number of initial words, since the target parturient may input by voice, there is a problem of colloquialism. After that, in order to improve the matching degree with the preset keyword library (each keyword is a standard word), the words are first subjected to word standardization conversion processing for the number of initial words.

[0057] As an example: convert "stomachache" to "abdominal pain".

[0058] The information sending unit 113 of the information collection robot 110 is used to send the target output word list to the information prompt module;

[0059] The information prompt module 120 is used to display each target output word in the target output word list.

[0060] Specifically, the information prompt module 120 can be set on the electronic device in the doctor's office, so that the doctor can obtain each target output word in the target output word list corresponding to the target parturient before diagnosing the target parturient this time. In this way, the words worthy of attention during the interaction between the target parturient and the information collection robot are collected, so as to assist relevant medical staff to determine the antenatal examination content and issue medical orders for the parturient according to the above-mentioned words worthy of attention, and enable relevant medical staff to pay attention to some parturient conditions that may be ignored according to the above-mentioned words worthy of attention, so as to ensure that the physical health indicators of each parturient during the entire pregnancy cycle are effectively monitored and timely adjusted. In addition, it is also possible to know some of the parturient's needs according to the above-mentioned words worthy of attention, so as to answer the parturient's questions within the limited consultation time and avoid missing some inquiry content during the consultation.

[0061] In an exemplary embodiment of the present application, the information analysis unit 112 of the information collection robot 110 is further used to analyze the historical medical order cooperation information and the user's personalized information to obtain a target cooperation degree interval corresponding to the target parturient; wherein, each cooperation degree interval has a corresponding medical order indication method; the medical order indication method corresponding to the target cooperation degree interval is the target medical order indication method.

[0062] Specifically, the information analysis unit is used to perform the following steps to obtain the target cooperation degree interval corresponding to the target parturient:

[0063] S270, according to the identity information of the target parturient and the historical medical order cooperation information, obtain the initial historical medical order cooperation degree corresponding to the target parturient.

[0064] Among them, the information collection robot 110 can be connected to the medical record information database of the hospital where it is located. The information analysis unit 112 of the information collection robot 110 is used to perform the following steps to obtain the initial historical medical order cooperation degree corresponding to the target parturient:

[0065] S271. Obtain the list of medical order items Y = (Y 1 , Y 2 , …, Y i , …, Y n ) corresponding to the most recent historical medical order of the target parturient according to the identity information of the target parturient; i = 1, 2, …, n; where n is the number of medical order items included in the list of medical order items corresponding to the most recent historical medical order from the current time; Y i is the item identifier corresponding to the i-th medical order item included in the list of medical order items corresponding to the most recent historical medical order from the current time; each medical order item in Y has a corresponding importance score.

[0066] Here, the information analysis unit 112 of the information collection robot 110 retrieves the historical medical order corresponding to the target parturient during the last antenatal examination according to the identity information of the target parturient; and obtains the corresponding list of medical order items Y. As an example: Y i may be "No strenuous exercise". In the whole medical order, the importance of different medical order items is different. As an example: the list of medical order items Y corresponding to the historical medical order = (Control blood sugar, Return for consultation in 1 week, Bring the results of blood sugar large profile + fasting urine routine + diet diary, Make an appointment for fetal echocardiogram, Iodine-rich diet, Count fetal movements by oneself at 28 weeks of pregnancy). Among them, according to the current physical health indicators of the target parturient, the importance corresponding to each medical order item may be different. If the current blood sugar index of the target parturient is high, then the importance score corresponding to "Control blood sugar" is high. If the current blood sugar index of the target parturient is slightly high, then the importance score corresponding to "Control blood sugar" is relatively low. And "Make an appointment for fetal echocardiogram" is a necessary examination, and its corresponding importance may be high. That is, for target parturients with different physical health indicators, the importance corresponding to the same medical order item may also be different. In summary, the importance score of each of the above medical order items is determined according to the corresponding physical health indicators of the parturient and each medical order item corresponding to the historical medical order. Further, it can be obtained according to a preset importance score determination model.

[0067] S272. Obtain the list of item cooperation degrees P = (P 1 , P 2 , …, P i , …, P n ) corresponding to Y based on Y and the historical medical order cooperation information; where P i is the item cooperation degree corresponding to Y i .

[0068] Here, according to the cooperation information of the historical medical order stated by the target parturient, obtain the item cooperation degree of each medical order item.

[0069] Among them, P i is determined according to the following steps:

[0070] Among them, if the corresponding medical order item is a first - type medical order item and the first target answer corresponding to this medical order item is an affirmative answer, then determine P i = 1; otherwise, determine P i = 0; where the first - type medical order item has two first preset answers; and the first target answer is one of the first preset answers.

[0071] In one embodiment, the first - type medical order item is a yes - or - no medical order item, that is, the preset answer of the corresponding medical order item is "yes" or "no". As an example: a certain medical order item is "Perform fetal heart ultrasound examination". If the first target answer corresponding to this medical order item is an affirmative answer, that is, "yes", then P i = 1; if the first target answer corresponding to this medical order item is a negative answer, that is, "no", then determine P i = 0.

[0072] However, if the corresponding medical order item is a second - type medical order item, then determine P according to the item compliance corresponding to each second preset answer of this medical order item and the second target answer corresponding to this medical order item i ; where 0 ≤ P i ≤ 1; and the second target answer is one of the second preset answers; the second - type medical order item has more than two second preset answers.

[0073] In one embodiment, the second - type medical order item is a select - type medical order item, that is, the preset answer of the corresponding medical order item is multiple options. As an example: a certain medical order item is "Control blood sugar", and the preset answers of the corresponding medical order item are "Completely controlled", "Generally controlled", and "Completely uncontrolled"; if the second target answer corresponding to this medical order item is "Completely controlled", then P i = 1; if the second target answer corresponding to this medical order item is "Generally controlled", then P i = 0.5; if the second target answer corresponding to this medical order item is "Completely uncontrolled", then P i = 0.

[0074] It should be noted that since the execution situation of many medical order items cannot be comprehensively covered by yes - or - no, in this embodiment, on the one hand, in order to obtain the cooperation situation of the parturient for each medical order item more objectively and accurately, corresponding preset option answers are set for each second - type medical order item, and corresponding score assignments are set for each preset option answer, so as to obtain the corresponding item compliance. On the other hand, it can avoid the waste of computing resources caused by natural language processing when the parturient answers without options. It is simpler, more convenient and more efficient.

[0075] S273. Obtain the initial historical doctor's order compliance CP corresponding to the target parturient according to Y, P, and the importance score corresponding to each doctor's order item, where CP meets the following conditions:

[0076] CP = Σ n i＝1 P i Z i

[0077] Where Z i is the normalized importance score corresponding to P i .

[0078] Here, initially obtain the overall compliance of the target parturient with the historical doctor's order according to the importance score corresponding to each doctor's order item and the item execution degree corresponding to each doctor's order item. Among them, P i Z i is the initial historical doctor's order compliance of the i-th doctor's order item in the historical doctor's order. Summing up the initial historical doctor's order compliance of each doctor's order item, the comprehensive initial historical doctor's order compliance of the target parturient for the entire historical doctor's order can be obtained.

[0079] It should be noted that since each doctor's order item has a corresponding importance score, and different doctor's orders include different doctor's order items, it is necessary to normalize the importance score corresponding to each doctor's order item in this historical doctor's order. As an example: the list of doctor's order items Y corresponding to the historical doctor's order = (Y 1 , Y 2 , Y 3 , Y 4 ); among them, the importance score corresponding to Y 1 is 8; the importance score corresponding to Y 2 is 5; the importance score corresponding to Y 3 is 3; the importance score corresponding to Y 4 is 4; normalizing each importance score, we get Z 1 = 1 / (8 + 5 + 3 + 4)×8 = 0.4; Z 2 = 100 / (8 + 5 + 3 + 4)×5 = 0.25; Z 3 = 100 / (8 + 5 + 3 + 4)×3 = 0.15; Z 4 = 100 / (8 + 5 + 3 + 4)×4 = 0.2. That is, adjust the total score to 1 point and make an adaptive adjustment of each importance score proportionally to obtain the normalized importance score, so that the total importance score corresponding to each doctor's order is the same, which is convenient for subsequent data calculation.

[0080] S280. Obtain the language confidence coefficient corresponding to the target parturient according to the identity information of the target parturient and the user's personalized information.

[0081] Here, the above historical medical order cooperation information is obtained by the information collection robot through interaction with the target parturient according to the historical medical orders of the target parturient and a preset question template, and is the self-report of the target parturient, that is, the self-assessment of the target parturient's cooperation degree with the historical will. Since the personality characteristics of each parturient are different, as an example: some parturients with more cautious personality characteristics may be more conservative in evaluating their cooperation degree with historical medical orders, that is, may be lower than the actual implementation degree; on the contrary, some parturients with more rough and exaggerated personality characteristics may be more exaggerated in evaluating their cooperation degree with historical medical orders, that is, may be higher than the actual implementation degree. The user personalized information reflects the personality characteristics of each user. Thus, the language confidence coefficient corresponding to the target parturient is obtained. The more conservative the user's self-assessment of the cooperation degree with the historical medical order, the higher the corresponding confidence coefficient; on the contrary, the more exaggerated the user's self-assessment of the cooperation degree with the historical medical order, the lower the corresponding confidence coefficient.

[0082] Furthermore, the information analysis unit is used to perform the following steps to obtain the language confidence coefficient corresponding to the target parturient:

[0083] S281, input the user personalized information of the target parturient into the target classification model.

[0084] S282, according to the target classification model, obtain the language confidence coefficient YZ corresponding to the target parturient; where YZ ∈ [SZ min , SZ max ; SZ min is the minimum value of YZ, -1 ≤ SZ min <0; SZ max is the maximum value of YZ, 0 < SZ min ≤1; and |SZ min | = |SZ max |.

[0085] Among them, the user personalized information is classified according to the target classification model, and the target classification model can be a natural language processing model, which can output the language confidence coefficient YZ corresponding to the target parturient by analyzing the user's personalized information (such as the user's speaking speed, attitude, etc.). When YZ is -1, it means that the confidence of the target parturient's speech is very low, that is, their self-assessment of the cooperation degree with the historical medical order may be very exaggerated and they like to exaggerate facts. On the contrary, when YZ is 1, it means that the confidence of the target parturient's speech is very high, that is, their self-assessment of the cooperation degree with the historical medical order may be very conservative.

[0086] According to the above language confidence coefficient, the historical medical order cooperation degree self-reported by the target parturient is corrected to obtain a more objective historical medical order cooperation degree.

[0087] S290. Obtain the target historical doctor's order compliance based on the initial historical doctor's order compliance and the language confidence coefficient.

[0088] Here, the target historical doctor's order compliance MD meets the following conditions:

[0089] MD = (1 + YZ) × CP.

[0090] That is, when YZ is -1, it indicates that the confidence of the target parturient in speaking is very low, that is, her own evaluation of the compliance with historical doctor's orders may be very exaggerated and she likes to exaggerate facts. At this time, the initial historical doctor's order compliance CP corresponding to the target parturient is corrected according to YZ. Since the confidence of the target parturient in speaking is very low, that is, what the target parturient says is basically untrustworthy, the target historical doctor's order compliance MD is determined to be 0. On the contrary, when YZ is 1, it indicates that the confidence of the target parturient in speaking is very high, that is, her own evaluation of the compliance with historical doctor's orders may be very conservative. Then multiply the initial historical doctor's order compliance by 2 to appropriately increase its corresponding initial historical doctor's order compliance so that it is closer to the real historical doctor's order compliance. And the above two extreme cases when YZ is -1 and YZ is 1. In one embodiment, the target classification model obtains the corresponding language confidence coefficient mostly in the interval [-1, 1] according to the input user personalized information, and corrects the initial historical doctor's order compliance according to the specific language confidence coefficient output by the target classification model, so that the obtained target historical doctor's order compliance is as objective and accurate as possible.

[0091] In this embodiment, by analyzing the obtained user personalized information corresponding to the target parturient, information such as the personality characteristics of the target parturient is obtained, and based on this, the self-reported historical doctor's order compliance degree of the target parturient is corrected to obtain the corresponding relatively objective compliance degree with historical doctor's orders.

[0092] S2100. Obtain the target compliance interval corresponding to the target parturient according to the target historical doctor's order compliance.

[0093] Among them, in this embodiment, several compliance intervals are preset, and each compliance interval has a corresponding doctor's order indication method; the doctor's order indication method corresponding to the target compliance interval is the target doctor's order indication method; the target historical doctor's order compliance belongs to the range of historical doctor's order compliance corresponding to the target compliance interval. That is, during prenatal examinations for parturients with different personality characteristics, medical staff will determine the corresponding doctor's order issuing method according to their personality characteristics and compliance with historical doctor's orders, so as to provide an adapted doctor's order issuing method for each parturient with different personality characteristics, improve the overall doctor's order compliance of pregnant and lying-in women, and ensure that the physical health indicators of each pregnant and lying-in woman in the entire pregnancy and childbirth cycle are effectively monitored and timely adjusted.

[0094] It should be noted that the doctor's order issuing method here can be: emphasizing key points, being detailed, etc.

[0095] In an exemplary embodiment of the present application, the information collection robot further includes a reminder unit.

[0096] The reminder unit is used to perform the following steps:

[0097] In response to receiving a medical appointment reminder during the interaction with the target parturient, the target parturient is prompted according to the medical appointment reminder.

[0098] Specifically, if a medical appointment reminder is received during the interaction with the target parturient, since the information collection robot can communicate with the devices in the doctor's office, the target parturient can be prompted to attend the appointment according to the medical appointment reminder.

[0099] The information sending unit 113 of the information collection robot 110 is further used to send the target medical order indication method to the information prompt module.

[0100] The information prompt module 120 is further used to display the target medical order prompt method.

[0101] Specifically, the information prompt module 120 can be set on the electronic device in the doctor's office, so that the doctor can obtain the execution situation of the historical medical orders of the target parturient and its corresponding personality situation before diagnosing the target parturient this time, and can adapt the corresponding target medical order prompt method for the corresponding target cooperation degree interval. This makes the acceptance and execution degree of the target parturient for the medical order higher.

[0102] In an exemplary embodiment of the present application, after step S272, the information analysis unit 112 of the information collection robot 110 is used to perform the following steps:

[0103] S274. According to Y, P, and the importance score corresponding to each medical order item, the key item cooperation degree list GP=(GP 1 , GP 2 , …, GP i , …, GP n ) is obtained; where GP i is the key item cooperation degree corresponding to Y i ; GP i meets the following conditions:

[0104] GP i =P i *Z i

[0105] Where Z i is the normalized importance score corresponding to P i .

[0106] S275. According to GP and YZ, obtain the corresponding list of matter standard compliance degrees BP = (BP 1 , BP 2 , …, BP i , …, BP n ); where BP i is the compliance degree of the key matter corresponding to Y i ; BP i meets the following conditions:

[0107] BP i = GP i *YZ.

[0108] Specifically, BP i represents the relatively objective compliance degree of the target parturient with respect to a certain medical order item in the historical medical order closest to the current time (considering the language confidence coefficient corresponding to the target parturient).

[0109] S276. According to BP and the preset standard compliance degree threshold, obtain the list of target medical order items MS = (MS 1 , MS 2 , …, MS c , …, MS d ); where MS c is the c-th target medical order item; the matter standard compliance degree corresponding to each target medical order item is less than the preset standard compliance degree threshold.

[0110] Specifically, the target medical order item is the medical order item with a relatively low compliance degree of the target parturient.

[0111] The information collection unit 111 is used to perform the following steps to obtain the set of physical state information lists F:

[0112] S002. Interact with the target parturient according to MS and the preset question list corresponding to each target medical order item to obtain the set of physical state information lists F = (F 1 , F 2 , …, F c , …, F d ).

[0113] Specifically, for the medical order items with a relatively low compliance degree of the target parturient, the information collection unit 111 of the information collection robot 110 continues to interact with the target parturient, and this interaction is for each of the above target medical order items.

[0114] In this embodiment, target medical advice items with a corresponding item standard compliance less than a preset standard compliance threshold are screened from the historical medical advice closest to the current time. Among them, the item standard compliance is obtained based on the item compliance, importance score, and language confidence coefficient of the target parturient corresponding to each medical advice item. The item standard compliance is positively correlated with the corresponding item compliance, importance score, and language confidence coefficient of the target parturient, so as to correct the key item compliance of each medical advice item according to the personality characteristics of the target parturient, and thus obtain a more objective and accurate item standard compliance.

[0115] In this embodiment, the item standard compliance corresponding to each medical advice item is obtained. If the corresponding item standard compliance is low, it indicates that the actual compliance of the target parturient with this medical advice item may be low. At this time, the information collection unit of the information collection robot interacts with the target parturient according to the preset question list corresponding to the medical advice item with a possibly low actual compliance. Among them, the questions in the preset question list can be index change type questions, that is, by secondary interaction, the changes brought by the medical advice item with a low actual compliance to the physical indicators of the target parturient can be determined, which can enable the doctor to obtain as much effective physical condition of the target parturient as possible before the consultation, so as to assist the doctor in diagnosis and medical advice issuance. On the other hand, it saves the doctor's consultation time, and can initially know the impact of the medical advice with a low actual compliance on the physical indicators of the target parturient, so that the doctor can adjust and monitor the corresponding treatment plan, and can timely discover possible problems of the parturient.

[0116] In an exemplary embodiment of the present application, an electronic device capable of implementing the above method is also provided.

[0117] Those skilled in the art of the relevant technical field can understand that various aspects of the present application can be implemented as a system, method, or program product. Therefore, various aspects of the present application can be specifically implemented in the following forms, namely: a complete hardware implementation, a complete software implementation (including firmware, microcode, etc.), or an implementation combining hardware and software aspects, which can be collectively referred to as "circuit", "module", or "system" here.

[0118] The electronic device according to this embodiment of the present application. The electronic device is only an example and should not bring any limitation to the functions and usage scope of the embodiments of the present application.

[0119] The electronic device is presented in the form of a general-purpose computing device. The components of the electronic device may include, but are not limited to: at least one of the above processors, at least one of the above memories, and a bus connecting different system components (including the memory and the processor).

[0120] Among them, the memory stores program code that can be executed by the processor, enabling the processor to execute the steps according to various exemplary embodiments of the present application described in the "Exemplary Method" section above of this specification.

[0121] The memory may include a readable medium in the form of a volatile memory, such as a random access memory (RAM) and / or a cache memory, and may further include a read-only memory (ROM).

[0122] The memory may also include a program / utility having a set (at least one) of program modules. Such program modules include, but are not limited to: an operating system, one or more application programs, other program modules, and program data. Each or some combination of these examples may include an implementation of a network environment.

[0123] The bus may represent one or more of several types of bus structures, including a memory bus or a memory controller, a peripheral bus, a graphics acceleration port, a processor, or a local bus using any of the various bus structures.

[0124] The electronic device may also communicate with one or more external devices (such as a keyboard, a pointing device, a Bluetooth device, etc.), may also communicate with one or more devices that enable a user to interact with the electronic device, and / or may communicate with any device that enables the electronic device to communicate with one or more other computing devices (such as a router, a modem, etc.). Such communication may be carried out through an input / output (I / O) interface. Moreover, the electronic device may also communicate with one or more networks (such as a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) through a network adapter. As shown in the figure, the network adapter communicates with other modules of the electronic device through the bus. It should be understood that although not shown in the figure, other hardware and / or software modules may be used in conjunction with the electronic device, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, etc.

[0125] Through the description of the above embodiments, those skilled in the art can easily understand that the exemplary embodiments described herein can be implemented by software, or can be implemented by a combination of software and necessary hardware. Therefore, the technical solution according to the embodiments of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (which can be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the embodiments of the present application.

[0126] In an exemplary embodiment of the present application, a computer-readable storage medium is further provided, on which a program product capable of implementing the above methods in this specification is stored. In some possible implementation manners, various aspects of the present application can also be implemented in the form of a program product, which includes program code. When the program product runs on a terminal device, the program code is used to cause the terminal device to execute the steps according to various exemplary embodiments described in the "Exemplary Method" section above of this specification.

[0127] The program product can adopt any combination of one or more readable media. The readable media can be a readable signal medium or a readable storage medium. The readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples (a non-exhaustive list) of the readable storage medium include: an electrical connection having one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0128] The computer-readable signal medium can include a data signal propagated in a baseband or as part of a carrier wave, which carries the readable program code. Such a propagated data signal can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The readable signal medium can also be any readable medium other than the readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device.

[0129] The program code included on the readable medium can be transmitted by any appropriate medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the above.

[0130] The program code for performing the operations of this application can be written in any combination of one or more programming languages. The programming languages include object-oriented programming languages such as Java, C++, etc., and also include conventional procedural programming languages such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computing device, partially on the user's device, executed as a stand-alone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server. In the case of a remote computing device, the remote computing device can be connected to the user's computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computing device (e.g., by using an Internet service provider to connect through the Internet).

[0131] In addition, the above-mentioned drawings are only schematic illustrations of the processes included in the method according to the exemplary embodiments of the present application, rather than for limiting purposes. It is easy to understand that the processes shown in the above-mentioned drawings do not indicate or limit the chronological order of these processes. Additionally, it is also easy to understand that these processes can be executed synchronously or asynchronously in, for example, multiple modules.

[0132] It should be noted that although several modules or units of the device for action execution are mentioned in the above detailed description, such a division is not mandatory. In fact, according to the embodiments of the present application, the features and functions of two or more of the above-mentioned modules or units can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units.

[0133] The above is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions that can be easily thought of by those skilled in the art within the technical scope disclosed by the present application should be covered by the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A maternity demand confirmation system, characterized in that: The system comprises: an information collection robot and an information prompt module; wherein the information collection robot comprises an information collection unit, an information analysis unit and an information sending unit; The information collection unit of the information collection robot is used to interact with the target parturient to obtain an output information list of the target parturient; The information analysis unit of the information collection robot is used to obtain a target output word list according to the output information list; wherein the target output word list includes a first target output word sublist and a second target output word sublist; the occurrence frequency corresponding to each of the first target output words in the first target output word sublist is equal to or greater than a preset frequency threshold; the occurrence frequency corresponding to each of the second target output words in the second target output word sublist is less than a preset frequency threshold, and each second target output word is the same as any preset focus word; the preset focus words are focus words corresponding to a number of abnormal pregnant women in history; The information sending unit of the information collection robot is used to send the target output word list to the information prompt module; The information prompt module is used to display each target output word in the target output word list; The information analysis unit is used to perform the following steps to obtain a first target output word sublist: S210, segmenting each output information in the output information list to obtain a number of initial words; S220, obtaining a plurality of intermediate words according to a preset keyword thesaurus; wherein the intermediate words are initial words that are the same as any keyword in the preset keyword thesaurus; S230, obtaining a first target output word sublist YL=(YL1, YL2, ..., YL j , …, YL m ), j = 1, 2, ..., m, where m is the number of the first target output words, YL j Output word for the jth first target; YL j The frequency of occurrence in the output information list is equal to or greater than a preset frequency threshold; After step S220, the information analysis unit is used to perform the following steps to obtain a second target output word sub-list: S240, obtaining a plurality of temporary words according to the plurality of intermediate words and a preset frequency threshold; wherein the temporary words are intermediate words whose appearance frequency in the output information list is less than the preset frequency threshold; S250, according to a plurality of temporary words and a preset determination method, obtain a corresponding second target output word sublist EL=(EL1, EL2, ..., EL p , …, EL q ), p = 1, 2, ..., q, where q is the number of the second target output words, EL p Output words for the pth second target; Each historical abnormal parturient has a corresponding abnormal parturient portrait; the preset determination method includes: S251, clustering is performed according to the abnormal maternal portraits corresponding to each of the several historical abnormal maternal women, so as to obtain a corresponding cluster list J=(J1, J2, ..., J x , …, J y ), x=1, 2, …, y, y is the number of clusters, J x is the cluster identifier corresponding to the xth cluster; each cluster includes at least one abnormal maternal portrait; each abnormal maternal portrait has a corresponding abnormal feature vector; each historical abnormal maternal has a corresponding preset attention word list; each cluster has a corresponding preset attention word list set; S252, according to the abnormal feature vector corresponding to each abnormal pregnant woman portrait contained in each cluster, obtain the cluster center vector list ZJ=(ZJ1, ZJ2, ..., ZJ x , …, ZJ y );Among them, ZJ x For J x The corresponding center vector; S253, obtaining a target feature vector MT of a target portrait corresponding to the target parturient; S254, according to MT and ZJ, obtain the key matching list MJ=(MJ1, MJ2, ..., MJ x , …, MJ y ); among them, MJ x For MT and ZJ x The degree of match between S255, if MJ x If it is greater than the preset matching threshold, J x Determine the target cluster; S256, will be with J x A temporary word that is identical to any preset focus word in the corresponding preset focus word list set is determined as a second target output word to obtain a second target output word sub-list EL.

2. The maternal needs confirmation system according to claim 1, characterized in that: MJ x Meet the following conditions: MJ x =(MT·ZJ x ) / (|MT|×|ZJ x |)。 3. The maternal needs confirmation system according to claim 1, characterized in that: The abnormal feature vector and the target feature vector are encoded according to one-hot encoding.

4. The maternal needs confirmation system according to claim 1, characterized in that: Each keyword in the preset keyword word library has a corresponding importance score; after step S230, the information analysis unit is further used to perform the following steps: S260, according to the importance score and the occurrence frequency of the keyword corresponding to each first target output word, the corresponding ranking priority XL=(XL1, XL2, ..., XL j ,…,XL m ), where XL j For YL j Corresponding ranking priority; XL j Meet the following conditions: XL j =YD j ×XP j Among them, YD j For YL j The importance of the corresponding keywords; XP j For YL j The frequency of occurrence of the corresponding keyword in the output information list.

5. The maternal needs confirmation system according to claim 1, characterized in that: The information collection robot also includes an information preprocessing unit, and the information processing unit is used to perform the following steps: Perform word standardization conversion processing on several initial words.

Images