Information processing method and device and electronic equipment

Abstract

The invention provides an information processing method and device and electronic equipment, and relates to the technical field of information, in particular to the technical field of child rearing guidance and infant monitoring. According to the specific implementation scheme, state information corresponding to a target infant is collected; analyzing the current state of the target infant according to the state information to obtain a state analysis result of the target infant; according to the state analysis result, obtaining a child rearing evaluation result corresponding to the state analysis result through a child rearing evaluation decision subject; wherein the child-rearing evaluation decision subject is at least one of a child-rearing evaluation rule engine and a child-rearing evaluation reasoning model.

Description

Technical Field

[0001] The present disclosure relates to the field of information processing technology, and in particular to the field of parenting guidance and infant monitoring technology. Background Art

[0002] Currently, parenting guidance products mainly rely on electronic parenting guides or parenting applications that require specific queries. Electronic parenting guides lack intelligent guidance; some parenting applications can only perform simple matching of conditions to solutions, so the parenting guidance solutions provided are single and poorly adaptable; other applications require a lot of analysis time and calculations, and are inefficient. Summary of the invention

[0003] The present disclosure provides an information processing method, device and electronic device for solving at least one of the above technical problems.

[0004] According to a first aspect of the present disclosure, there is provided an information processing method, wherein the method comprises:

[0005] Collecting status information corresponding to the target infant;

[0006] Analyze the current state of the target infant according to the state information to obtain a state analysis result of the target infant;

[0007] According to the status analysis result, a parenting assessment decision-making subject obtains a parenting assessment result corresponding to the status analysis result;

[0008] The parenting assessment decision-making body is a parenting assessment rule engine and at least one sound cloning model in the parenting assessment inference model, which is used to output cloned sound synthesis data that is similar to the timbre of the user's voice sample.

[0009] According to a second aspect of the present disclosure, there is provided an information processing device, wherein the device comprises:

[0010] A collection module, used to collect status information corresponding to the target baby;

[0011] An analysis module, configured to analyze the current state of the target infant according to the state information to obtain a state analysis result of the target infant;

[0012] A decision-making module, configured to obtain, according to the status analysis result, a parenting assessment result corresponding to the status analysis result through a parenting assessment decision-making subject;

[0013] Among them, the parenting assessment decision-making subject is at least one of a parenting assessment rule engine and a parenting assessment reasoning model.

[0014] According to a third aspect of the present disclosure, there is provided an electronic device, including:

[0015] at least one processor; and

[0016] a memory communicatively connected to the at least one processor; wherein,

[0017] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the above method.

[0018] According to a fourth aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to cause the computer to execute the above method.

[0019] According to a fifth aspect of the present disclosure, a computer program product is provided, comprising a computer program, wherein the computer program implements the above method when executed by a processor.

[0020] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure.

[0022] Figure 1 is a flowchart of an information processing method provided by the first embodiment of the present disclosure;

[0023] Figure 2 is a flowchart of an information processing method provided by the second embodiment of the present disclosure;

[0024] Figure 3 is an exemplary flow chart of S205;

[0025] Figure 4 is an exemplary flow chart of S207;

[0026] Figure 5 is an exemplary flow chart of S207B;

[0027] Figure 6 is an exemplary flow chart of method 1;

[0028] Figure 7 is an exemplary flow chart of the second method;

[0029] Figure 8is a structural schematic diagram of an information processing device provided by the third embodiment of the present disclosure;

[0030] Fig. 9 The block diagram is a block diagram of an electronic device for implementing the method of the embodiment of the present disclosure. DETAILED DESCRIPTION

[0031] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0032] In the absence of conflict, the various embodiments of the present disclosure and the various features therein may be combined with each other.

[0033] As used herein, the term "and / or" includes any and all combinations of one or more of the associated listed items.

[0034] The terminology used herein is for describing particular embodiments only and is not intended to limit the present disclosure.As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.

[0035] Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by those of ordinary skill in the art. It will also be understood that terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant art and the present disclosure, and will not be interpreted as having an idealized or overly formal meaning unless explicitly defined as such herein.

[0036] The information processing method according to the present disclosure can be executed by an electronic device such as a terminal device or a server, and the terminal device can be a vehicle-mounted device, a user equipment (User Equipment, UE), a mobile device, a user terminal, a terminal, a cellular phone, a cordless phone, a personal digital assistant (Personal Digital Assistant, PDA), a handheld device, a computing device, a vehicle-mounted device, a wearable device, etc. The method can be implemented by a processor calling a computer-readable program instruction stored in a memory. Alternatively, the information processing method provided by the present disclosure can be executed by a server.

[0037] In the first embodiment disclosed, see Figure 1 , Figure 1 A flowchart of an information processing method provided by the first embodiment of the present disclosure is shown, and the method includes:

[0038] S101. Collect status information corresponding to the target baby.

[0039] S102: Analyze the current state of the target infant according to the state information to obtain a state analysis result of the target infant.

[0040] S103. According to the status analysis result, a parenting assessment decision-making subject obtains a parenting assessment result corresponding to the status analysis result.

[0041] The parenting assessment decision subject is used to obtain the corresponding parenting assessment result according to the state analysis result, so as to guide the user to implement the parenting assessment result to solve the needs of the infant corresponding to the state analysis result. The parenting assessment decision subject can be at least one of the parenting assessment rule engine and the parenting assessment reasoning model.

[0042] The parenting assessment rule engine takes the state analysis result as input, and determines the parenting assessment result corresponding to the state analysis result based on the preset rules in the preset parenting assessment rule library. The parenting assessment rule library presets multiple rules, logical reasoning relationships between rules, and reasoning results (i.e., parenting assessment results). The process of determining the parenting assessment result corresponding to the state analysis result is specifically as follows: through the condition matching algorithm, the current input state analysis result is used as a condition, and the rules are matched with the preset rules. In other words, the state analysis result is compared with the rules, and the rules that meet the current state analysis result are retrieved, and the corresponding parenting assessment result is obtained according to the logical reasoning relationship of the rules. The parenting assessment rule engine can quickly and clearly handle problems with clear logic, so that when the conditional emotions or complexity of the state analysis results are not high, the parenting assessment results can be quickly obtained through rule matching.

[0043] The parenting assessment reasoning model is obtained by training a deep learning model using a state analysis result set and a parenting assessment result label set as training data. The deep learning model may use, for example, a long short-term memory network, a convolutional neural network, or a reinforcement learning model for decision-making, which is not limited here. The parenting assessment reasoning model can handle problems with ambiguous conditions or high complexity, and can learn based on complex or ambiguous state analysis results to obtain corresponding parenting assessment results.

[0044] The present disclosure adopts the above-mentioned method to make decisions on parenting assessment results by using two methods: a parenting assessment rule engine and a parenting assessment reasoning model, thereby providing a dual-channel decision-making mechanism. It can choose to use a parenting assessment rule engine that is good at handling logically clear problems to generate parenting assessment results and obtain parenting assessment results efficiently. It can also use a deep learning-based parenting assessment reasoning model that is good at handling fuzzy problems to generate parenting assessment results to cope with the processing of complex states. It can also make decisions by combining the two, taking into account both the efficiency and accuracy of the decision, so that different decision-making methods can be selected according to the collected state of the baby to give parenting assessment results, thereby being able to adapt to a variety of scenarios and having the decision-making advantages of both the rule engine and the deep learning model.

[0045] The infant's status information is information indicating the infant's own status or the status of the environment the infant is in. It can be single-modal or multi-modal.

[0046] In some examples, S01 collects state information as multimodal state information, and the multimodal state information includes at least one of the following: sound state information, image state information, biometric state information, environmental state information, etc.

[0047] The sound state information can be collected by a sound collection device, for example, a high-sensitivity microphone array is set around the target baby, the microphone array can effectively capture sound signals from different directions, and use beamforming technology to enhance the main sound signal. The sound state information may include at least one of the sound state information of the baby and the sound state information of the environment. After the sound state information is collected, it can be subjected to noise reduction processing to eliminate background noise.

[0048] The image state information can be collected by an image acquisition device, such as a high-resolution camera, a motion capture camera, an infrared night vision camera, etc., which are not limited here. After collecting multiple frames of image state information, the multiple frames of image state information can be sorted according to time sequence.

[0049] The biometric state information may include various biological signals indicating the physiological state of the infant, which may be collected through a variety of biological signal sensors, such as: collecting heart rate state information through a heart rate sensor; collecting body temperature state information through a body temperature sensor, etc., which are not limited here. After the biometric state information is collected, it may be pre-processed through a low-pass filter, a Kalman filter algorithm, etc., to filter out noise data and abnormal data.

[0050] Environmental status information can be various types of information that characterize the environment in which the baby is located, which can be collected through sensors or image acquisition devices, for example: collecting environmental temperature status information through a temperature sensor; collecting environmental humidity status information through a humidity sensor; collecting environmental brightness status information, information about people contained in the environment, etc. through an image acquisition device, without limitation here.

[0051] Among them, the state analysis result is the analysis result obtained by understanding and analyzing the state information, and the state analysis result may include: the behavior state of the baby obtained by behavior recognition based on the state information; the emotional state of the baby obtained by emotion recognition based on the state information, etc., which are not limited here. Performing a preliminary understanding and analysis of the state information to obtain the state analysis result, and then inputting the state analysis result into the parenting assessment decision-making subject, can effectively reduce the complexity of the decision and reduce the amount of calculation of the parenting assessment decision-making subject.

[0052] In some examples, S103 includes:

[0053] According to the historical state analysis results of the target infant and the corresponding historical parenting assessment results, the long-term behavioral state information of the target infant, and the state analysis results, the parenting assessment results are obtained by the parenting assessment decision-making subject.

[0054] In the present disclosure, in addition to making decisions based on the current state analysis results, the personalized data of the baby can also be introduced, and personalized decisions can be made in combination with the state analysis results, so that the parenting assessment results made by the decision are more suitable for the individual baby. Specifically, the historical decisions corresponding to the baby, that is, the historical state analysis results and the corresponding historical parenting assessment results, as well as the long-term behavioral state information representing the long-standing regular behavior of the baby can be referred to. In this way, dynamic adjustments are made to make the parenting assessment results made by the decision more accurate. For example, it is determined through long-term behavioral state information that the baby is usually awake between 2 and 3 in the morning. Even if the current state analysis result does not identify the baby's active behavior, a parenting assessment result will be generated to prompt the user to check the baby's status.

[0055] In some examples, long-term behavioral state information is obtained according to:

[0056] Arrange the historical status analysis results of the target infant within a preset period of time in time series;

[0057] The long-term behavior pattern of the target infant is analyzed based on the sorted state analysis results, and the long-term behavior state information is obtained according to the analysis results.

[0058] The method provided by the present invention can track and analyze the long-term behavior of infants. After the historical status analysis results accumulated by the target infant within a preset time period are collected, the historical status analysis results are organized into time-series data, and then the behavior recognition is performed on them to extract the long-term behavior pattern of the target infant individual to obtain long-term behavior status information, so as to use the long-term behavior status information as the personalized parameter of the infant and add it to the input of the decision to generate the parenting assessment result.

[0059] It should be noted that in the method provided by the present disclosure, the parenting assessment result can be expressed in various forms. For example, the parenting assessment result is an assessment result obtained by further in-depth analysis of the infant's status analysis result, which is used to deeply and multi-dimensionally represent the infant's current status; for another example, the parenting assessment result can be a parenting suggestion corresponding to the infant's status obtained from the infant's status analysis result, which is used to provide parenting guidance to users, improve the infant's current adverse status, and meet the infant's needs, which is not limited here. In addition, the data form of the parenting assessment result can be structured information or information in natural language form, which is not limited here.

[0060] In some examples, the parenting assessment result is specifically a parenting suggestion. Accordingly, the parenting assessment decision-making subject is used to obtain the parenting suggestion based on the state analysis result. Among them, the output of the parenting assessment rule engine is the parenting suggestion; the output of the parenting assessment reasoning model is the parenting suggestion. For the sake of ease of explanation, the following uses the parenting assessment result as the parenting suggestion, the parenting assessment decision-making subject, the parenting assessment rule engine, and the output of the parenting assessment reasoning model as the parenting suggestion as an example, but it does not constitute a limitation to the present disclosure. The "parenting suggestion" described in the present disclosure can be replaced with "parenting assessment result".

[0061] In disclosing the second embodiment, see Figure 2 , Figure 2 A flow chart of a method for intelligently generating parenting advice provided by a second embodiment of the present disclosure is shown, the method comprising:

[0062] S201, collecting state information of each modality corresponding to the target infant, and performing time synchronization processing on the state information of each modality.

[0063] Since the state information of each modality is collected by different devices, there may be clock differences or collection delays in the systems of each collection device. In order to facilitate the subsequent processing of multi-modal state information, the state information of each modality can be synchronized first. Specifically, the timestamp mechanism can be used to ensure that the data of each modality is aligned at each time point.

[0064] It should be noted that S201 is one implementation of S101. S101 may have other implementations, which are not limited here.

[0065] S202: Perform feature fusion based on the state information of each mode after time synchronization to obtain a fused state feature vector.

[0066] Specifically, a cross-modal attention mechanism can be used to fuse the features of the state information of each modality to obtain a state feature vector with a unified representation, thereby unifying the feature representation of the state information of each modality and facilitating subsequent feature extraction and recognition.

[0067] S203: Perform dimensionality reduction processing on the state feature vector.

[0068] Through dimensionality reduction processing, redundant information and low-correlation features of the state feature vector are removed, reducing the complexity of subsequent calculations.

[0069] S204, extracting high-dimensional features of the state feature vector after dimensionality reduction processing according to principal component analysis (PCA) and autoencoder.

[0070] By extracting high-dimensional features, the core information of the state analysis results can be further extracted and more complex nonlinear feature relationships can be captured.

[0071] Through S202-S204, accurate feature extraction can be performed on the state analysis results, which facilitates the accuracy of subsequent analysis based on the extracted features and can reduce the amount of data analyzed.

[0072] S205. Analyze the current state of the target infant based on the high-dimensional features to obtain a state analysis result of the target infant.

[0073] For some examples, see Figure 3 , Figure 3 An exemplary flow chart of S205 is shown. The state analysis result includes: the behavior state and emotional state of the baby, wherein S205 includes:

[0074] S2051. Analyze the current state of the target infant based on high-dimensional features to obtain the behavioral state of the target infant.

[0075] In some examples, S2051 may be:

[0076] The high-dimensional features are used as input, and the output behavior state is obtained through the behavior state recognition model.

[0077] Among them, the behavior state recognition model can collect one of the convolutional neural network or the long short-term memory network, or a hybrid model of the two.

[0078] The behavior state is information indicating the current behavior of the target baby. For example, the behavior state may include: crying state, elevated body temperature state, hand and foot activity state, etc., which are not limited here.

[0079] S2052. Identify based on the behavioral state to obtain the current emotional state of the target infant.

[0080] Based on the identified behavioral state, the emotional state of the target infant can be further identified through a sentiment analysis model, wherein the sentiment analysis model can be a model using a convolutional neural network or a long short-term memory network or a hybrid thereof, or a large model.

[0081] In some examples, S2052 includes:

[0082] The behavioral state is input into the big model and the output emotional state is obtained.

[0083] The emotional state is information indicating the current emotion of the target infant. For example, the emotional state may include: a happy state, a sleepy state, a hungry state, a painful state, etc., which are not limited here.

[0084] It should be noted that S202-S205 is one implementation of S102. There are other implementations of S102, which are not limited here.

[0085] S206: Determine the complexity level of the status analysis result.

[0086] S207. According to the complexity level, determine at least one of the parenting assessment rule engine and the parenting assessment reasoning model as the parenting assessment decision-making subject, and input the state analysis result into the parenting assessment decision-making subject to obtain parenting suggestions.

[0087] Among them, multiple complexity levels can be preset, such as a first complexity level and a second complexity level with increasing complexity. When the complexity level is not high, a single parenting assessment rule engine can be used for decision-making, so that a decision solution can be quickly obtained through condition matching. When the complexity level is high, parenting advice decisions can be made through a parenting assessment reasoning model, or by combining a parenting assessment rule engine with a parenting assessment reasoning model, so that the parenting advice is sufficiently accurate.

[0088] The complexity level can be obtained according to at least one of the following: the data volume of the state analysis result, the number of state types of the state analysis result, the semantic clarity of the state analysis result, etc. The larger the data volume of the current state analysis result, the more state types there are, such as including multiple behavioral states and emotional states, and the lower the semantic clarity, in other words, when the logical conditions are unclear, the higher the complexity of the problem, that is, the higher the complexity level.

[0089] It should be noted that S206-S207 is one implementation of S103, and there are other implementations of S103, which are not limited here.

[0090] For some examples, see Figure 4 , Figure 4 An exemplary flow chart of S207 is shown. S207 includes:

[0091] In a less complex way:

[0092] S207A, when the complexity level meets the first complexity level, the parenting assessment rule engine is used as the parenting assessment decision-making subject, and the state analysis results are input into the parenting assessment rule engine for rule matching, and parenting suggestions are obtained according to the rule matching results.

[0093] In cases with lower complexity, a single parenting assessment rule engine can be used to make decisions, so that a decision solution can be quickly obtained through condition matching.

[0094] Before S201, a parenting evaluation rule base of a parenting evaluation rule engine needs to be established. That is, before S201, the method further includes:

[0095] Step 1: Establish a parenting assessment rule library, and preset multiple rules and corresponding parenting suggestions in the parenting assessment rule library.

[0096] Among them, rules can be configured in a variety of ways, and users can also customize the logical reasoning relationship between rules and their corresponding parenting suggestions. For example, Rule 1 is that the number of crying times exceeds the limit, and Rule 2 is that the feeding interval is longer than the limit; if the current status analysis results meet Rule 1 and Rule 2, the matching parenting suggestion is: it is recommended to feed the baby.

[0097] In some examples, in step 1, presetting multiple rules in the parenting assessment rule library and the parenting suggestions corresponding to the rules may include:

[0098] Sub-step 1: Acquire knowledge data from a medical knowledge base, generate multiple rules based on the knowledge data, and store them in a parenting assessment rule base.

[0099] The knowledge data in the medical knowledge base can be semantically identified to obtain multiple rule conditions. Specifically, in some examples, the knowledge data includes at least one of the following: standard status information of the infant, abnormal symptom information of the infant, and currently, other knowledge data can also be included, which is not limited here. Among them, the standard status information of the infant can include at least one of the following: standard body temperature of the infant, standard feeding amount of the infant, and standard sleep time of the infant; the abnormal status information of the infant can include: abnormal heart rate limit, abnormal body temperature limit, etc., which are not limited here.

[0100] According to the identified knowledge data after semantic extraction, rules are generated based on the knowledge data. For example, the multiple rules include at least one of the following:

[0101] The status analysis results conform to the standard status information.

[0102] Status analysis results do not include abnormal symptom information.

[0103] Therefore, after obtaining the infant's status analysis results, the status can be compared with the standard status in the medical knowledge base, and it can be determined whether it includes abnormal symptom status, so as to obtain professional parenting advice.

[0104] The method provided by the present disclosure also includes:

[0105] Obtain updated information from the medical knowledge base and update the rules of the parenting assessment rule base based on the updated information, thereby ensuring the real-time and accuracy of the rules.

[0106] Currently, other rules may also be included, which are not limited here.

[0107] In some examples, based on the above, S207A specifically includes:

[0108] The status analysis results are input into the parenting assessment rule engine. In the parenting assessment rule library, the status analysis results are matched based on preset rules, and parenting suggestions are obtained based on the matching results.

[0109] In the present disclosure, a plurality of rules, logical reasoning relationships between the rules, and reasoning results, i.e., parenting suggestions, are preset in the parenting assessment rule library. The process of determining the parenting suggestions corresponding to the state analysis results is specifically as follows: through the condition matching algorithm, the state analysis results currently input are used as conditions, and the rules are matched with the preset rules. In other words, the state analysis results are compared with the rules, the rules that meet the current state analysis results are retrieved, and the corresponding parenting suggestions are obtained according to the logical reasoning relationship of the rules. The parenting assessment rule engine can quickly and clearly handle problems with clear logic, so that when the conditional emotions or complexity of the state analysis results are not high, parenting suggestions can be quickly obtained through rule matching.

[0110] Furthermore, in a more complex way:

[0111] S207B, when the complexity level meets the second complexity level, at least the parenting assessment reasoning model is used as the parenting assessment decision-making subject, and the state analysis results are input into the parenting assessment reasoning model to obtain output parenting suggestions.

[0112] In cases with a higher level of complexity, parenting advice can be obtained through a single parenting assessment reasoning model, or parenting advice decisions can be made by combining a parenting assessment rule engine and a parenting assessment reasoning model, thereby making the parenting advice sufficiently accurate.

[0113] The complexity of the second complexity level is greater than that of the first complexity level.

[0114] The following is an example of combining the parenting assessment rule engine and the parenting assessment reasoning model to make parenting advice decisions.

[0115] For some examples, see Figure 5 , Figure 5 An exemplary flow chart of S207B is shown, and S207B specifically includes:

[0116] S207B1. When the complexity level meets the second complexity level, the parenting assessment rule engine and the parenting assessment reasoning model are used as the parenting assessment decision-making subjects.

[0117] S207B2. Input the status analysis results into the parenting assessment rule engine and the parenting assessment reasoning model to obtain output parenting suggestions.

[0118] In some examples, S207B2 includes two methods.

[0119] Method 1: Hierarchical decision-making mechanism

[0120] See also Figure 6 , Figure 6 An exemplary flow chart of method 1 is shown. S207B2 includes:

[0121] S011. Input the status analysis results into the parenting assessment rule engine for rule matching, determine the redundant data in the status analysis results based on the rule matching results, perform data trimming on the status analysis results, and remove the redundant data.

[0122] The parenting assessment rule engine is used to remove some data with clear logical rules from the state analysis results. For example, if the state analysis results show that the target baby has just eaten and is in a happy emotional state, the rule engine can exclude data related to the hunger state in the state analysis results, thereby achieving data trimming and reducing the amount of data processed by the model.

[0123] S012. Input the trimmed state analysis results into the parenting assessment reasoning model to obtain output parenting suggestions.

[0124] The parenting assessment reasoning model can further conduct a comprehensive analysis on the trimmed status analysis results, accurately identify the infant's status, and obtain accurate parenting recommendations.

[0125] In this way, by implementing a layer-by-layer hierarchical decision-making mechanism, the problem is first processed by the rule engine for primary processing, and then a higher-level judgment is made through the deep learning model layer, thereby improving the feasibility of handling complex problems and improving response efficiency.

[0126] Method 2: Hybrid decision-making mechanism

[0127] See also Figure 7 , Figure 7 An exemplary flow chart of the second method is shown. S207B2 includes:

[0128] S021. Input the status analysis result into the parenting assessment rule engine to obtain the first parenting suggestion.

[0129] S022. Input the status analysis results into the parenting assessment reasoning model to obtain the second parenting suggestion.

[0130] S023. Combine the first parenting suggestion and the second parenting suggestion to obtain the final parenting suggestion.

[0131] In some cases, when it is necessary to deal with complex situations with multiple variables and dimensions, the decision-making of the rule engine and the model can be combined to provide the best parenting advice. In some examples, the first parenting advice (also referred to as the first parenting evaluation result) and the second parenting advice (also referred to as the second parenting evaluation result) can be semantically fused to obtain the final parenting advice.

[0132] In some examples, S203 includes:

[0133] Step 1: According to the first weight and the first parenting suggestion of the parenting assessment rule engine, the second weight and the second parenting suggestion of the parenting assessment reasoning model, the first parenting suggestion and the second parenting suggestion are integrated to obtain the final parenting suggestion.

[0134] In the present disclosure, different weights may be set for the parenting assessment rule engine and the parenting assessment reasoning model, so as to be able to flexibly adapt to more application scenarios.

[0135] It should be noted that the ratio of the first weight and the second weight can be adjusted adaptively. Specifically, before the parenting evaluation decision subject obtains the parenting advice corresponding to the status analysis result according to the status analysis result, the method further includes:

[0136] Step A: Determine the ratio of the first weight to the second weight based on at least one of the complexity level, the importance of the current task of generating parenting advice, and the overlap between the current state analysis result and the historical state analysis result.

[0137] Among them, the proportion of the second weight is positively correlated with the complexity level and importance. In other words, the higher the complexity level and the higher the importance of the task, the higher the second weight of the model; and the proportion of the second weight is negatively correlated with the overlap. In other words, the lower the overlap, the newer the current decision-making problem and status, and the unfamiliar decision-making task for the parenting advice decision-maker. Therefore, the higher the proportion of the second weight of the model, the more efficient and accurate comprehensive decision-making solutions can be obtained through such adaptive adjustments.

[0138] Continue to see Figure 2 After S207, the method further includes:

[0139] S208. Perform language processing on the parenting suggestions through natural language generation (NLG) technology to obtain the parenting suggestions after language processing.

[0140] In the implementation of S208, the parenting advice (also called parenting assessment results) obtained by the parenting advice decision-making subject is structured information. Through NLG technology, the structured parenting advice can be converted into parenting advice described in natural language, so that users can understand the parenting advice more intuitively.

[0141] It should be noted that in some examples, S208 can be omitted. For example, when the output result of the parenting advice decision-making entity is a parenting advice described in natural language (also called a parenting assessment result), the output parenting advice can be directly applied without natural language conversion. This is not limited here.

[0142] S209: Generate a display page for the user.

[0143] In some examples, S209 includes:

[0144] Sub-step 1: based on the status analysis result, generating a display page for displaying the status of the target baby;

[0145] Sub-step 2: Based on the parenting suggestions, generate a display page for displaying the parenting suggestions.

[0146] In order to increase user visibility, a display page showing the baby's status can be generated based on the status analysis results. The page can include various status analysis results in the form of graphics, tables, animations, etc., which are not limited here. Correspondingly, a display page for parenting suggestions can also be generated, in which the parenting suggestions can be converted into animation form to guide users to implement the parenting suggestions in the form of teaching animations.

[0147] In some examples, the display page of parenting advice may add interactive components, and users may perform interactive operations through the interactive components. The interactive operations may include, for example: feedback information operation; modification of parenting advice operation, etc., which are not limited here.

[0148] S210. Optimize the parenting assessment decision-making subject based on feedback information.

[0149] In some examples, S210 includes:

[0150] Sub-step 1: Obtain and save feedback information triggered by parenting suggestions within a preset time period.

[0151] Sub-step 2: Based on the feedback information within a preset time period, adjust the rules of the parenting assessment rule engine, and / or adjust the model parameters of the parenting assessment reasoning model.

[0152] Among them, the feedback information includes at least one of the following: feedback information input by the user based on the parenting suggestions. The user can input feedback information through the interactive components of the display interface, for example, a score for the accuracy of the parenting suggestions; environmental feedback information of the target baby obtained after the user executes the parenting suggestions. After obtaining the parenting suggestions, the baby's environmental information can be collected as environmental feedback information through an image acquisition device or sensor. For example, when a parenting suggestion for coaxing a baby to sleep is generated and the parenting suggestion is determined and executed, sound status information is collected through a microphone array as environmental feedback information to determine whether the baby's crying has decreased.

[0153] In the present disclosure, feedback information of parenting suggestions can be continuously collected, and the rules of the rule engine and the model parameters of the reasoning model can be optimized based on the feedback information, so that the reasoning process is more accurate and.

[0154] In disclosing the third embodiment, see Figure 8 ,like Figure 1 The principle shown, Figure 8 A schematic diagram of the structure of an information processing device 80 provided in the third embodiment of the present disclosure is shown, and the device includes:

[0155] A collection module 801 is used to collect status information corresponding to the target baby;

[0156] An analysis module 802 is used to analyze the current state of the target baby according to the state information to obtain a state analysis result of the target baby;

[0157] A decision module 803 is used to obtain a parenting assessment result corresponding to the status analysis result through a parenting assessment decision subject according to the status analysis result;

[0158] Among them, the parenting assessment decision-making subject is at least one of a parenting assessment rule engine and a parenting assessment reasoning model.

[0159] In some examples, the decision module is specifically used to:

[0160] Determine the complexity level of the state analysis results;

[0161] According to the complexity level, at least one of the parenting assessment rule engine and the parenting assessment reasoning model is determined as the parenting assessment decision-making subject, and the state analysis result is input into the parenting assessment decision-making subject to obtain the parenting assessment result.

[0162] In some examples, the decision module specifically includes:

[0163] The first decision submodule is used for, when the complexity level meets the first complexity level, using the parenting assessment rule engine as the parenting assessment decision subject, inputting the state analysis result into the parenting assessment rule engine for rule matching, and obtaining the parenting assessment result according to the rule matching result;

[0164] A second decision-making submodule is used for, when the complexity level meets the second complexity level, at least using the parenting assessment reasoning model as the parenting assessment decision subject, and inputting the state analysis result into the parenting assessment reasoning model to obtain the output parenting assessment result;

[0165] The complexity of the second complexity level is greater than that of the first complexity level.

[0166] In some examples, the apparatus further comprises:

[0167] A rule establishment module is used to establish a parenting assessment rule base, and preset multiple rules and parenting assessment results corresponding to the rules in the parenting assessment rule base;

[0168] The first decision submodule is specifically used for:

[0169] The status analysis results are input into the parenting assessment rule engine. In the parenting assessment rule library, the status analysis results are matched based on preset rules, and the parenting assessment results are obtained according to the matching results.

[0170] In some examples, the first decision submodule is specifically used to:

[0171] Acquire knowledge data in a medical knowledge base, generate multiple rules based on the knowledge data, and store them in a parenting assessment rule base;

[0172] The knowledge data includes at least one of the following: standard status information of the infant, abnormal symptom information of the infant;

[0173] The multiple rules include at least one of the following: the state analysis result complies with standard state information; the state analysis result does not include abnormal symptom information.

[0174] In some examples, the second decision submodule is specifically used to:

[0175] When the complexity level meets the second complexity level, the parenting assessment rule engine and the parenting assessment reasoning model are used as the parenting assessment decision-making subjects;

[0176] The state analysis results are input into the parenting assessment rule engine and the parenting assessment reasoning model to obtain the output parenting assessment results.

[0177] In some examples, the second decision submodule is specifically used to:

[0178] Input the status analysis results into the parenting assessment rule engine for rule matching, determine the redundant data in the status analysis results based on the rule matching results, perform data trimming on the status analysis results, and remove the redundant data;

[0179] The trimmed state analysis results are input into the parenting assessment reasoning model to obtain the output parenting assessment results.

[0180] In some examples, the second decision submodule is specifically used to:

[0181] Inputting the status analysis result into a parenting assessment rule engine to obtain a first parenting assessment result;

[0182] Inputting the state analysis result into the parenting assessment reasoning model to obtain a second parenting assessment result;

[0183] The first parenting assessment result and the second parenting assessment result are combined to obtain a final parenting assessment result.

[0184] In some examples, the second decision submodule is specifically used to:

[0185] According to the first weight and the first parenting assessment result of the parenting assessment rule engine, the second weight and the second parenting assessment result of the parenting assessment reasoning model, the first parenting assessment result and the second parenting assessment result are fused to obtain the final parenting assessment result.

[0186] In some examples, the apparatus further comprises:

[0187] A weight module, configured to determine a ratio of the first weight to the second weight according to at least one of a complexity level, an importance of a task currently generating a parenting assessment result, and a degree of overlap between a current state analysis result and a historical state analysis result;

[0188] The proportion of the second weight is positively correlated with the complexity level and importance, and negatively correlated with the overlap.

[0189] In some examples, the decision module is specifically configured to:

[0190] According to the historical state analysis results of the target infant and the corresponding historical parenting assessment results, the long-term behavioral state information of the target infant, and the state analysis results, the parenting assessment results are obtained by the parenting assessment decision-making subject.

[0191] In some examples, long-term behavioral state information is obtained according to:

[0192] Arrange the historical status analysis results of the target infant within a preset period of time in time series;

[0193] The long-term behavior pattern of the target infant is analyzed based on the sorted state analysis results, and the long-term behavior state information is obtained according to the analysis results.

[0194] In some examples, the state information is multimodal state information, and the multimodal state information includes at least one of the following:

[0195] Sound status information, image status information, biometric status information, and environment status information.

[0196] In some examples, the acquisition module is specifically used to:

[0197] The state information of each modality corresponding to the target infant is collected, and the state information of each modality is time-synchronized.

[0198] In some examples, the analysis module is specifically configured to:

[0199] Perform feature fusion based on the state information of each mode after time synchronization to obtain a fused state feature vector;

[0200] Perform dimension reduction on the state feature vector;

[0201] Extract high-dimensional features of the state feature vector after dimensionality reduction processing based on principal component analysis and autoencoder;

[0202] The current state of the target infant is analyzed based on high-dimensional features to obtain a state analysis result of the target infant.

[0203] In some examples, the state analysis results include: the infant's behavioral state and affective state;

[0204] When the analysis module analyzes the current state of the target baby based on the high-dimensional features and obtains the state analysis result of the target baby, it is specifically used to:

[0205] Analyze the current state of the target baby based on high-dimensional features to obtain the behavioral state of the target baby;

[0206] Based on the behavioral state, the current emotional state of the target infant is obtained.

[0207] In some examples, the analysis module is specifically used to:

[0208] The behavioral state is input into the big model and the output emotional state is obtained.

[0209] In some examples, the parenting assessment results in parenting recommendations;

[0210] The parenting assessment decision-making subject is used to obtain parenting suggestions based on the status analysis results;

[0211] Among them, the output of the parenting assessment rule engine is parenting advice; the output of the parenting assessment reasoning model is parenting advice.

[0212] In some examples, the apparatus further comprises:

[0213] The natural language module is used to perform language processing on the parenting assessment results through natural language generation technology to obtain the parenting assessment results after language processing.

[0214] In some examples, the apparatus further comprises:

[0215] A display module, used for generating a display page for displaying the status of the target baby based on the status analysis result;

[0216] Based on the child-rearing evaluation results, a display page for displaying the child-rearing evaluation results is generated.

[0217] In some examples, the apparatus further comprises:

[0218] A feedback adjustment module, used to obtain and save feedback information triggered by parenting evaluation results within a preset period of time;

[0219] Based on the feedback information within a preset time period, adjusting the rules of the parenting assessment rule engine, and / or adjusting the model parameters of the parenting assessment reasoning model;

[0220] The feedback information includes at least one of the following: feedback information input by the user based on the parenting assessment result; and environmental feedback information of the target baby obtained after the user executes the parenting assessment result.

[0221] In the technical solution disclosed herein, the acquisition, storage and application of user personal information involved are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0222] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium, a computer program product and an autonomous driving vehicle.

[0223] The computer instructions of the non-transitory computer-readable storage medium storing computer instructions are used to make a computer execute the above method.

[0224] A computer program product comprises a computer program, which implements the above method when executed by a processor.

[0225] Fig. 9 A schematic block diagram of an example electronic device 900 that can be used to implement an embodiment of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0226] like Fig. 9 As shown, the device 900 includes a computing unit 901, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 902 or a computer program loaded from a storage unit into a random access memory (RAM) 903. In the RAM 903, various programs and data required for the operation of the device 900 can also be stored. The computing unit 901, the ROM 902, and the RAM 903 are connected to each other via a bus 904. An input / output (I / O) interface 905 is also connected to the bus 904.

[0227] A number of components in the device 900 are connected to the I / O interface 905, including: an input unit 906, such as a keyboard, a mouse, etc.; an output unit 907, such as various types of displays, speakers, etc.; a storage unit 908, such as a disk, an optical disk, etc.; and a communication unit 909, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 909 allows the device 900 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0228] The computing unit 901 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 901 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 901 performs the various methods and processes described above, such as information processing methods. For example, in some embodiments, the information processing method may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 908. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 900 via the ROM 902 and / or the communication unit 909. When the computer program is loaded into the RAM 903 and executed by the computing unit 901, one or more steps of the information processing method described above may be performed. Alternatively, in other embodiments, the computing unit 901 may be configured as an information processing method in any other appropriate manner (e.g., by means of firmware).

[0229] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0230] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0231] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer 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 foregoing.

[0232] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0233] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0234] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0235] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0236] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. An information processing method, wherein: The method comprises: Collecting status information corresponding to the target infant; Analyze the current state of the target infant according to the state information to obtain a state analysis result of the target infant; According to the status analysis result, a parenting assessment decision-making subject obtains a parenting assessment result corresponding to the status analysis result; Among them, the parenting assessment decision-making subject is at least one of a parenting assessment rule engine and a parenting assessment reasoning model.

2. The method according to claim 1, wherein: The step of obtaining a parenting assessment result corresponding to the status analysis result through a parenting assessment decision-making subject according to the status analysis result includes: determining a complexity level of the state analysis result; According to the complexity level, at least one of the parenting assessment rule engine and the parenting assessment reasoning model is determined as the parenting assessment decision-making subject, and the state analysis result is input into the parenting assessment decision-making subject to obtain the parenting assessment result.

3. The method according to claim 2, wherein: The step of determining at least one of the parenting assessment rule engine and the parenting assessment reasoning model as the parenting assessment decision subject according to the complexity level, and inputting the state analysis result into the parenting assessment decision subject to obtain the parenting assessment result includes: When the complexity level meets the first complexity level, the parenting assessment rule engine is used as the parenting assessment decision-making subject, and the state analysis result is input into the parenting assessment rule engine for rule matching, and the parenting assessment result is obtained according to the rule matching result; When the complexity level meets the second complexity level, at least the parenting assessment reasoning model is used as the parenting assessment decision-making subject, and the state analysis result is input into the parenting assessment reasoning model to obtain the output parenting assessment result; The complexity of the second complexity level is greater than that of the first complexity level.

4. The method according to claim 3, wherein: Before collecting the status information corresponding to the target infant, the method further includes: Establishing a parenting assessment rule base, and presetting a plurality of rules and parenting assessment results corresponding to the rules in the parenting assessment rule base; When the complexity level meets the first complexity level, the parenting assessment rule engine is used as the parenting assessment decision-making subject, and the state analysis result is input into the parenting assessment rule engine for rule matching, and the parenting assessment result is obtained according to the rule matching result, including: The state analysis result is input into the parenting assessment rule engine, and in the parenting assessment rule library, the state analysis result is matched based on the preset rules, and the parenting assessment result is obtained according to the matching result.

5. The method according to claim 4, wherein: The plurality of rules preset in the parenting assessment rule base and the parenting assessment results corresponding to the rules include: Acquiring knowledge data from a medical knowledge base, generating the plurality of rules based on the knowledge data, and storing the rules in the parenting assessment rule base; Wherein, the knowledge data includes at least one of the following: standard status information of the infant, abnormal symptom information of the infant; The multiple rules include at least one of the following: the state analysis result complies with the standard state information; the state analysis result does not include the abnormal symptom information.

6. The method according to any one of claims 3 to 5, wherein: When the complexity level meets the second complexity level, at least the parenting assessment reasoning model is used as the parenting assessment decision-making subject, and the state analysis result is input into the parenting assessment reasoning model to obtain the output parenting assessment result, including: When the complexity level meets the second complexity level, the parenting assessment rule engine and the parenting assessment reasoning model are used as the parenting assessment decision-making subject; The state analysis result is input into the parenting assessment rule engine and the parenting assessment reasoning model to obtain the output parenting assessment result.

7. The method according to claim 6, wherein: The step of inputting the state analysis result into the parenting assessment rule engine and the parenting assessment reasoning model to obtain the output parenting assessment result includes: Inputting the state analysis result into the parenting assessment rule engine for rule matching, determining redundant data in the state analysis result according to the rule matching result, and performing data trimming on the state analysis result to remove the redundant data; The trimmed state analysis results are input into the parenting assessment reasoning model to obtain the output parenting assessment results.

8. The method according to claim 6, wherein: The step of inputting the state analysis result into the parenting assessment rule engine and the parenting assessment reasoning model to obtain the output parenting assessment result includes: Inputting the state analysis result into the parenting assessment rule engine to obtain a first parenting assessment result; Inputting the state analysis result into the parenting assessment reasoning model to obtain a second parenting assessment result; The first parenting assessment result and the second parenting assessment result are combined to obtain the final parenting assessment result.

9. The method according to claim 8, wherein: The combining the first parenting assessment result and the second parenting assessment result to obtain the final parenting assessment result includes: According to the first weight of the parenting assessment rule engine and the first parenting assessment result, the second weight of the parenting assessment reasoning model and the second parenting assessment result, the first parenting assessment result and the second parenting assessment result are fused to obtain the final parenting assessment result.

10. The method according to claim 9, wherein: Before obtaining the parenting assessment result corresponding to the status analysis result through the parenting assessment decision subject according to the status analysis result, the method further includes: determining a ratio of the first weight to the second weight according to at least one of the complexity level, the importance of the task currently generating the parenting assessment result, and the overlap between the current status analysis result and the historical status analysis result; The ratio of the second weight is positively correlated with the complexity level and the importance, and negatively correlated with the overlap.

11. The method according to any one of claims 1 to 10, wherein: According to the status analysis result, a parenting assessment result corresponding to the status analysis result is obtained by a parenting assessment decision-making subject, including: According to the historical state analysis results of the target infant and the corresponding historical parenting assessment results, the long-term behavioral state information of the target infant, and the state analysis results, the parenting assessment result is obtained by the parenting assessment decision-making subject.

12. The method according to claim 11, wherein: The long-term behavior status information is obtained in the following manner: Sorting the historical status analysis results of the target infant within a preset period of time in time series; The long-term behavior pattern of the target infant is analyzed based on the sorted state analysis results, and the long-term behavior state information is obtained according to the analysis results.

13. The method according to any one of claims 1 to 12, wherein: The state information is multimodal state information, and the multimodal state information includes at least one of the following: Sound status information, image status information, biometric status information, and environmental status information.

14. The method according to claim 13, wherein: The collecting of the status information corresponding to the target infant includes: The state information of each modality corresponding to the target infant is collected, and the state information of each modality is time-synchronized.

15. The method according to claim 14, wherein: Analyzing the current state of the target infant according to the state information to obtain a state analysis result of the target infant includes: Perform feature fusion based on the state information of each mode after time synchronization to obtain a fused state feature vector; Performing dimensionality reduction processing on the state feature vector; Extracting high-dimensional features of the state feature vector after dimensionality reduction processing according to principal component analysis and autoencoder; The current state of the target infant is analyzed based on the high-dimensional features to obtain a state analysis result of the target infant.

16. The method according to claim 15, wherein: The state analysis results include: the behavioral state and emotional state of the infant; The step of analyzing the current state of the target infant based on the high-dimensional features to obtain a state analysis result of the target infant includes: analyzing the current state of the target infant based on the high-dimensional features to obtain the behavioral state of the target infant; Based on the behavioral state, identification is performed to obtain the current emotional state of the target infant.

17. The method according to claim 16, wherein: The identifying based on the behavioral state to obtain the current emotional state of the target infant includes: The behavioral state is input into the large model to obtain the output emotional state.

18. The method according to any one of claims 1 to 17, wherein: The parenting assessment result is a parenting suggestion; The parenting assessment decision-making subject is used to obtain the parenting advice according to the status analysis result; Among them, the output of the parenting assessment rule engine is the parenting advice; the output of the parenting assessment reasoning model is the parenting advice.

19. The method according to any one of claims 1 to 17, wherein: After obtaining a parenting assessment result corresponding to the status analysis result through a parenting assessment decision-making subject according to the status analysis result, the method includes: The parenting assessment result is language processed by natural language generation technology to obtain the parenting assessment result after language processing.

20. The method according to any one of claims 1 to 19, wherein: After obtaining a parenting assessment result corresponding to the status analysis result through a parenting assessment decision-making subject according to the status analysis result, the method includes: Based on the status analysis result, generating a display page for displaying the status of the target baby; Based on the child-rearing evaluation result, a presentation page for presenting the child-rearing evaluation result is generated.

21. The method according to any one of claims 1 to 20, wherein: After obtaining a parenting assessment result corresponding to the status analysis result through a parenting assessment decision-making subject according to the status analysis result, the method includes: Obtaining and saving feedback information triggered by the parenting assessment results within a preset period of time; Based on the feedback information within a preset time period, adjusting the rules of the parenting assessment rule engine, and / or adjusting the model parameters of the parenting assessment reasoning model; The feedback information includes at least one of the following: feedback information input by the user based on the parenting assessment result; and environmental feedback information of the target baby obtained after the user executes the parenting assessment result.

22. An information processing device, wherein: The device comprises: A collection module, used to collect status information corresponding to the target baby; An analysis module, configured to analyze the current state of the target infant according to the state information to obtain a state analysis result of the target infant; A decision-making module, configured to obtain, according to the status analysis result, a parenting assessment result corresponding to the status analysis result through a parenting assessment decision-making subject; Among them, the parenting assessment decision-making subject is at least one of a parenting assessment rule engine and a parenting assessment reasoning model.

23. An electronic device, comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 20.

24. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1-20.

25. A computer program product comprising a computer program, which, when executed by a processor, implements the method according to any one of claims 1 to 20.

Images