Task result prediction method and device, electronic equipment and storage medium

Abstract

The application discloses a task result prediction method and device, electronic equipment and a storage medium. The method comprises the following steps: determining target structure data of a target task; and obtaining a prediction result of the target task based on the target structure data and a task result prediction model. The task result prediction model comprises an encoding layer and at least one task layer. Since the actual data is data containing building-related physical meaning, the target structure data is converted from the actual data and simulation data corresponding to the target task according to the data structure of the task result prediction model. Therefore, the application inputs the target structure data into the task result prediction model to obtain an accurate prediction result of the target task, solves the problem that the task prediction result is inaccurate due to the fact that the physical data cannot be accurately represented in the model, and realizes accurate prediction of the task result.

Description

Technical Field

[0001] This invention relates to the field of architectural simulation, and more particularly to a method, apparatus, electronic device, and storage medium for predicting task outcomes. Background Technology

[0002] Currently, the model used in building simulation is a mathematical model abstracted from a physical model. The prediction of task results is made using the above mathematical model. The above mathematical model is a simplified physical expression to varying degrees. If the mathematical model is highly simplified, although the numerical prediction results in some aspects can be made more accurate through verification with actual data, the numerical prediction results in terms of physical aspects are still relatively low, resulting in low accuracy and reasonableness of the prediction results. Therefore, it is very important to ensure the accuracy of the prediction results. Summary of the Invention

[0003] This invention provides a method, apparatus, electronic device, and storage medium for predicting task results, in order to solve the problem of inaccurate task prediction results caused by the inability of physical data to be accurately represented in the model, and to achieve accurate prediction of task results.

[0004] According to one aspect of the present invention, a method for predicting task outcomes is provided, the method comprising:

[0005] The target structure data for the target task is determined. This target structure data is derived from the actual and simulated data corresponding to the target task based on the data structure of the task result prediction model. The actual data contains data with physical meaning related to the building.

[0006] Based on the target structure data and the task result prediction model, the prediction result of the target task is obtained;

[0007] The task result prediction model includes an encoding layer and at least one task layer, with the task layer located after the encoding layer. The encoding layer is used to encode structural data and output object feature encoding. The task layer is used to calculate the object feature encoding to obtain the prediction result of the target task, where a task includes at least one type of object.

[0008] According to another aspect of the present invention, a task outcome prediction apparatus is provided, the apparatus comprising:

[0009] The data determination module is used to determine the target structure data of the target task. The target structure data is derived from the actual data and simulated data corresponding to the target task based on the data structure of the task result prediction model. The actual data contains data with physical meaning related to the building.

[0010] The prediction module is used to obtain the prediction result of the target task based on the target structure data and the task result prediction model;

[0011] The task result prediction model includes an encoding layer and at least one task layer, with the task layer located after the encoding layer. The encoding layer is used to encode structural data and output object feature encoding. The task layer is used to calculate the object feature encoding to obtain the prediction result of the target task, where a task includes at least one type of object.

[0012] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0013] At least one processor; and

[0014] A memory communicatively connected to the at least one processor; wherein,

[0015] The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the task result prediction method according to any embodiment of the present invention.

[0016] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the task result prediction method according to any embodiment of the present invention.

[0017] The technical solution of this invention includes a task result prediction model comprising an encoding layer and at least one task layer, with the task layer located after the encoding layer. The encoding layer encodes structural data and outputs object feature encodings. The task layer calculates the object feature encodings to obtain the prediction results of the target task. The encoding layer achieves accurate encoding of different data, and different task layers accurately predict the task results of different tasks based on the object feature encodings output by the encoding layer. Since the actual data contains data with physical meaning related to the building, and the target structural data is transformed from the actual data and simulated data corresponding to the target task based on the data structure of the task result prediction model, this invention can obtain accurate prediction results of the target task by inputting the target structural data into the task result prediction model. This solves the problem of inaccurate task prediction results caused by the inability to accurately represent physical data in the model, and achieves accurate prediction of task results.

[0018] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 This is a flowchart of a task result prediction method provided by an embodiment of the present invention;

[0021] Figure 2 This is a flowchart illustrating the structural data transformation process applicable to embodiments of the present invention;

[0022] Figure 3 This is a flowchart of another task result prediction method provided by an embodiment of the present invention;

[0023] Figure 4 This is a flowchart illustrating the coding layer calculation process applicable to embodiments of the present invention;

[0024] Figure 5 This is a flowchart illustrating the task-level computation process applicable to embodiments of the present invention.

[0025] Figure 6 This is a schematic diagram of the structure of a task result prediction device according to an embodiment of the present invention;

[0026] Figure 7 This is a schematic diagram of the structure of an electronic device that implements the task result prediction method of the present invention according to an embodiment of the present invention. Detailed Implementation

[0027] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0028] It should be noted that the terms "target," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0029] Example 1

[0030] Figure 1 This is a flowchart of a task result prediction method provided in an embodiment of the present invention. This embodiment can be applied to predicting various tasks that may exist in building simulation. The prediction results reflect the physical mechanism of the building and its interior. This method can be executed by a task result prediction device, which can be implemented in hardware and / or software. The task result prediction device can be configured in any electronic device with network communication function.

[0031] like Figure 1 As shown, the task result prediction method of the present invention includes the following steps:

[0032] S110. Determine the target structure data for the target task.

[0033] The target structure data is derived from the actual and simulated data corresponding to the target task based on the data structure of the task result prediction model. This target structure data reflects the physical mechanisms of the building. For example, in the field of architecture, design, renovation, system control, operation evaluation, and maintenance evaluation all require data reflecting the physical mechanisms of the building, because data related to physical mechanisms can make the prediction results more accurate. The actual data contains data with physical meaning related to the building.

[0034] The task result prediction model includes an encoding layer and at least one task layer, with the task layer following the encoding layer. The encoding layer encodes the structured data and outputs object feature codes, which can be 64-bit encodings. The task layer calculates the object feature codes to obtain the prediction result for the target task, where each task includes at least one type of object.

[0035] The task outcome prediction model can be trained using structured data based on historical stages. The structured data is derived from the actual and simulated data corresponding to the target task based on the data structure of the task outcome prediction model. The actual data contains data with physical meaning related to buildings. That is, the data in this invention is not solely based on simulated or actual data. It also breaks down the barriers between different simulation software and incorporates a large amount of building data generated by various software simulations into the large model training, thereby ensuring that the prediction results of the task outcome prediction model are more accurate.

[0036] The target task can be understood as a task related to the building that reflects the changing state of objects in the project. For example, the target task could be a task that predicts building energy consumption, predicts cooling load, HVAC control actions, system equipment fault diagnosis (classification), and the impact of equipment operation and maintenance frequency on energy consumption prediction.

[0037] Specifically, the process involves acquiring actual and simulated data for the target task, and then transforming this data into target structured data based on data transformation relationships. These data transformation relationships define the correspondence between actual and simulated data and structured data, representing the data in the structural form of a task outcome prediction model without affecting the physical nature of the data.

[0038] As an optional but non-limiting approach, the target structure data for the objective task is determined, including the following steps A1-A4:

[0039] Step A1: Obtain multi-dimensional data for the target task, including actual data and simulated data.

[0040] Specifically, simulation data can be understood as the simulation data of the target task by various simulation software related to the target task; actual data can be understood as the data of the actual project related to the target task, which includes physically significant data of interest to the target task, and the physically significant data is of great importance to the implementation of the target task. Therefore, the model prediction process needs to be able to analyze the impact of relevant physical data well.

[0041] Step A2: Extract at least one type of target object from the multi-dimensional data of the target task, and extract the static and dynamic data corresponding to the target object from the multi-dimensional data of the target task.

[0042] Static data refers to data that does not change over time, while dynamic data refers to data that changes over time.

[0043] Specifically, each target task can contain multiple types of target objects; that is, multiple types of target objects and the relationships between them constitute a target task. Dynamic data can be understood as data that changes over time; it is a dynamic process that can effectively reflect changes in the target task.

[0044] Step A3: Based on the data structure of the task result prediction model, integrate the static and dynamic data corresponding to at least one type of target object to determine the target relationship data, target static data, and target dynamic data of at least one type of target object corresponding to the target task.

[0045] Among them, relational data is used to describe the degree of association between different classes of objects that are related.

[0046] Specifically, such as Figure 2 As shown, the data transformation process is as follows: After extracting the static and dynamic data corresponding to at least one type of target object, in order to enable the data to be processed more quickly using the task result prediction model, it is necessary to transform the static and dynamic data corresponding to at least one type of target object into data with a data structure similar to that of the task result prediction model. That is, based on the data structure of the task result prediction model, the static and dynamic data corresponding to at least one type of target object are transformed into target static and target dynamic data of at least one type of target object corresponding to the target task. Furthermore, relational data is used to describe the degree of association between different types of objects that are related. Therefore, it is necessary to establish the association between the target static and target dynamic data of at least one type of target object, and this association includes the association with temporal changes, thereby obtaining the target relational data of at least one type of target object corresponding to the target task.

[0047] As an optional but non-limiting approach, the static and dynamic data corresponding to at least one target object are integrated to determine the target relationship data, target static data, and target dynamic data of at least one type of target object corresponding to the target task, including the following steps B1-B2:

[0048] Step B1: Determine the data structure transformation table corresponding to different types of objects, and transform the static and dynamic data corresponding to the target object according to the data structure transformation table to obtain the target static data and target dynamic data of at least one type of object corresponding to the target task.

[0049] Among them, the data structure transformation table establishes the data structure transformation relationship between different types of objects and their corresponding static and dynamic data according to the data structure in the task result prediction model.

[0050] Step B2: Determine the relationship list of different types of objects. Based on the relationship list, static data and dynamic data corresponding to at least one type of target object, determine the target relationship data of at least one type of target object corresponding to the target task.

[0051] The relationship list describes different types of objects that are related. For example, it can be used to calculate spatial connectivity based on coordinate data or to calculate connectivity between spaces based on the presence or absence of doors or windows. The relationship data describes the degree of association between different types of objects, including changes over time.

[0052] The technical solution of this embodiment transforms the static and dynamic data corresponding to the target object by using a data structure transformation table and a relationship list, thereby obtaining the target static data, target dynamic data, and target relationship data of the target task. This ensures that the data contains sufficient physical data and that the data can be well integrated with the task result prediction model.

[0053] Step A4: Use the target static data, target dynamic data, and target relationship data as the target structure data for the target task.

[0054] This embodiment's technical solution acquires multi-dimensional data of the target task, extracts at least one type of target object from the multi-dimensional data, and extracts static and dynamic data corresponding to the target object. Static data is data that does not change over time, while dynamic data is data that changes over time. This embodiment's extraction of static and dynamic data can effectively distinguish the trend of data change, facilitating rapid subsequent data processing. Furthermore, based on the data structure of the task result prediction model, the static and dynamic data corresponding to at least one target object are integrated to determine the target relationship data, target static data, and target dynamic data of at least one type of target object corresponding to the target task. The relationship data is used to describe the degree of association between different types of related objects. The target static data, target dynamic data, and target relationship data are used as the target structure data of the target task. This invention transforms data into data that conforms to the processing of the task result prediction model, ensuring the accuracy of the task result prediction model's predictions.

[0055] S120. Based on the target structure data and the task result prediction model, obtain the prediction results of the target task.

[0056] Specifically, the task result prediction model can reflect the correspondence between structural data and prediction results. Therefore, by acquiring the target structural data and inputting it into the task result prediction model, the model will output the prediction results of the target task, and the prediction results can well reflect the relevant physical meaning contained in the target task.

[0057] The technical solution of this invention includes a task result prediction model comprising an encoding layer and at least one task layer, with the task layer located after the encoding layer. The encoding layer encodes structural data and outputs object feature encodings. The task layer calculates the object feature encodings to obtain the prediction results of the target task. The encoding layer achieves accurate encoding of different data, and different task layers accurately predict the task results of different tasks based on the object feature encodings output by the encoding layer. Since the actual data contains data with physical meaning related to the building, and the target structural data is transformed from the actual data and simulated data corresponding to the target task based on the data structure of the task result prediction model, this invention can obtain accurate prediction results of the target task by inputting the target structural data into the task result prediction model. This solves the problem of inaccurate task prediction results caused by the inability to accurately represent physical data in the model, and achieves accurate prediction of task results.

[0058] Example 2

[0059] Figure 3 This is a flowchart of another task result prediction method provided by an embodiment of the present invention. The technical solution of this embodiment further optimizes the process of S120 in the above embodiment based on the above embodiment. This embodiment can be combined with various optional solutions in one or more of the above embodiments.

[0060] like Figure 3 As shown, the task result prediction method of the present invention includes the following steps:

[0061] S210. Determine the target structure data for the target task.

[0062] Among them, the target structure data is derived from the actual data and simulated data corresponding to the target task based on the data structure of the task result prediction model; the actual data contains data with physical meaning related to the building.

[0063] The task result prediction model includes an encoding layer and at least one task layer, with the task layer located after the encoding layer. The encoding layer is used to encode the structural data and output object feature encoding. The task layer is used to calculate the object feature encoding to obtain the prediction result of the target task. A task includes at least one type of object.

[0064] S220. Input the target structure data into the task result prediction model. The encoding layer in the task result prediction model encodes the target structure data to obtain the target object feature code corresponding to each type of target object in the preset time period.

[0065] The preset time period is the time period between the current moment and a preset time after the current moment.

[0066] Specifically, the target structure data includes the structure data of each target object corresponding to the target task. The encoding layer can reflect the correlation between the target structure data of the target task and the object feature codes of each target object corresponding to the target task. Moreover, the correlation includes a time series relationship. Therefore, when the target structure data is input into the task result prediction model, the encoding layer in the task result prediction model can encode the target structure data to obtain the target object feature codes of each type of target object corresponding to the target task in a preset time period.

[0067] As an optional but non-limiting embodiment, the encoding layer in the task outcome prediction model includes an information encoding layer, a graph encoding layer, and a time-series encoding layer. The encoding layer performs encoding operations on the data sequentially according to the information encoding layer, graph encoding layer, and time-series encoding layer. The information encoding layer encodes data at different times, the graph encoding layer encodes data based on relational data, and the time-series encoding layer encodes data within a time period. Relational data describes the degree of association between different classes of objects that are related. The task outcome prediction model is a neural network model, and its encoding layer includes an information encoding layer, a graph encoding layer, and a time-series encoding layer. This allows for encoding of structural data at three levels, making the final object feature encoding more reflective of the physical meaning inherent in the structural data itself.

[0068] As an optional but non-limiting embodiment, the encoding layer in the task result prediction model encodes the target structure data to obtain the target object feature encoding for each type of target object corresponding to the target task within a preset time period, including the following steps C1-C3:

[0069] Step C1: The information encoding layer in the task result prediction model encodes the target static data and target dynamic data of each type of object to obtain the first object feature code corresponding to each type of target object at different times.

[0070] Specifically, the information encoding layer is the basic encoding of structural data, that is, it transforms structural data into a 64-bit object feature encoding form. Target structural data includes at least one type of target object's static data and target dynamic data, specifically, such as... Figure 4 As shown, the information encoding layer in the task result prediction model encodes the static target data of each type of object, and the information encoding layer in the task result prediction model encodes the dynamic target data of each type of object at different times, thereby obtaining the first object feature encoding corresponding to each type of target object at different times.

[0071] Step C2: Based on the relational data corresponding to each type of target object, the graph coding layer in the task result prediction model encodes the first object feature code to obtain the second object feature code corresponding to each type of object at different times.

[0072] Specifically, the graph coding layer encodes the relationships between structural data. The various objects in the target task have different degrees of correlation. To accurately predict the target task, it is necessary to reflect the relationships between the first object feature codes corresponding to each type of target object at different times. Therefore, such as... Figure 4 As shown, it is necessary to introduce the relational data corresponding to each type of target object. The graph coding layer in the task result prediction model encodes the first object feature code corresponding to each type of object at different times based on the relational data corresponding to each type of target object, and obtains the second object feature code corresponding to each type of object at different times. The second object feature code can reflect the correlation between structural data.

[0073] Step C3: The time series encoding layer in the task result prediction model encodes the second object feature code within a preset time period to obtain the target object feature code for each type of target object corresponding to the target task within the preset time period. The preset time period is the time period between the current time and the preset time after the current time.

[0074] Specifically, the time series coding layer can reflect the influence between structural data in different time periods and the degree of influence on the prediction results. Therefore, such as Figure 4 As shown, the time series encoding layer in the task result prediction model encodes the second object feature code within a preset time period to obtain the target object feature code for each type of target object corresponding to the target task within the preset time period.

[0075] The technical solution in this embodiment encodes the target structure data of the target task through the information coding layer, graph coding layer and time series coding layer in the task result prediction model, which can fully combine static information, dynamic data and relational data to make the prediction more accurate.

[0076] S230. In the task result prediction model, the task layer corresponding to the target task calculates the feature encoding of the target object to obtain the prediction result of the target task.

[0077] Specifically, such as Figure 5 As shown, one task layer corresponds to one target task. The task layer can reflect the relationship between the object feature encoding of each target object corresponding to the target task and the prediction result of the target task. Therefore, in the task result prediction model, the task layer corresponding to the target task can calculate the target object feature encoding to obtain the prediction result of the target task.

[0078] Optionally, to ensure the accuracy of the task result prediction model, the task result prediction model may include cue word units. The cue word units are used to store task-related physical data, which serves as cue words to fine-tune the parameters of the coding layer in the task result prediction model.

[0079] The introduction of cue words can be determined by assessing whether the target structural data is sufficient to identify a unique physical world mechanism. If so, no cue word is introduced; otherwise, or if there is room for fine-tuning, a cue word is introduced. Furthermore, cue words can be generated for different object types, relationships between object types, and temporal aspects. For example, architectural cue words could include information about the building's surrounding environment and its regional functionality; temporal cue words could include extracted short-time sequence codes.

[0080] Specifically, prompt words are used to fine-tune the parameters of the encoding layer in the task result prediction model. The process can be one of two things: First, reserve prompt word positions in the encoding vectors of each layer, and directly fill these positions with the input prompt word encoding to fine-tune the parameters of the encoding layer in the task result prediction model. Second, build a separate neural network layer to fine-tune the parameters from the prompt words to each layer of the larger model.

[0081] Optionally, the performance of the task result prediction model may degrade over long-term use. Therefore, it is advisable to periodically acquire structural data of historical time periods prior to the current moment and use it as training data to update the task result prediction model, thereby ensuring its accuracy.

[0082] The technical solution of this invention includes a task result prediction model comprising an encoding layer and at least one task layer, with the task layer located after the encoding layer. The encoding layer encodes structural data and outputs object feature codes. The task layer calculates the object feature codes to obtain the prediction result of the target task. The encoding layer accurately encodes different data, and different task layers accurately predict the task results of different tasks based on the object feature codes output by the encoding layer. Since the actual data contains data with physical meaning related to buildings, and the target structural data is transformed from the actual data and simulated data corresponding to the target task according to the data structure of the task result prediction model, this invention inputs the target structural data into the task result prediction model. The encoding layer in the task result prediction model encodes the target structural data to obtain the target object feature codes corresponding to each type of target object in a preset time period, thus fully combining the data in the target structural data. Furthermore, the task layer corresponding to the target task in the task result prediction model calculates the target object feature codes to obtain the prediction result of the target task, solving the problem of inaccurate task prediction results caused by the inability to accurately represent physical data in the model, and achieving accurate prediction of task results.

[0083] Example 3

[0084] Figure 6 This is a schematic diagram of a task result prediction device provided in an embodiment of the present invention. This embodiment is applicable to predicting various tasks that may exist in building simulation. The prediction results reflect the building and its internal physical mechanisms. This task result prediction device can be implemented in hardware and / or software and can be configured in any electronic device with network communication capabilities. Figure 3 As shown, the device includes:

[0085] The data determination module 310 is used to determine the target structure data of the target task. The target structure data is derived from the actual data and simulated data corresponding to the target task based on the data structure of the task result prediction model. The actual data contains data with physical meaning related to the building.

[0086] The prediction module 320 is used to obtain the prediction result of the target task based on the target structure data and the task result prediction model;

[0087] The task result prediction model includes an encoding layer and at least one task layer, with the task layer located after the encoding layer. The encoding layer is used to encode structural data and output object feature encoding. The task layer is used to calculate the object feature encoding to obtain the prediction result of the target task, where a task includes at least one type of object.

[0088] Based on the above embodiments, optionally, the data determination module includes:

[0089] A data acquisition unit is used to acquire multi-dimensional data of the target task, including actual data and simulated data;

[0090] A data extraction unit is configured to extract at least one type of target object from the multi-dimensional data of the target task, and to extract static and dynamic data corresponding to the target object from the multi-dimensional data of the target task; the static data is data that does not change over time, and the dynamic data is data that changes over time.

[0091] The data integration unit is used to integrate static and dynamic data corresponding to at least one target object according to the data structure of the task result prediction model, and to determine target relationship data, target static data and target dynamic data of at least one type of object corresponding to the target task. The relationship data is used to describe the degree of association between different types of objects that are related.

[0092] The target structure data combination unit is used to combine the target static data, target dynamic data and target relationship data as the target structure data of the target task.

[0093] Based on the above embodiments, optionally, the data integration unit is used for:

[0094] A data structure transformation table is determined for different types of objects. Based on the data structure transformation table, the static and dynamic data corresponding to the target object are transformed to obtain the target static data and target dynamic data of at least one type of object corresponding to the target task. The data structure transformation table is a data structure transformation relationship between different types of objects and their corresponding static and dynamic data established according to the data structure in the task result prediction model.

[0095] A list of relationships between different types of objects is determined. Based on the list of relationships, static data and dynamic data corresponding to at least one of the target objects, target relationship data for at least one type of object corresponding to the target task is determined. The list of relationships is used to describe different types of objects that are related, and the relationship data is used to describe the degree of association between different types of objects that are related.

[0096] Based on the above embodiments, optionally, the prediction module includes:

[0097] An encoding unit is used to input the target structure data into the task result prediction model. The encoding layer in the task result prediction model encodes the target structure data to obtain the target object feature code corresponding to each type of target object in the target task within a preset time period. The preset time period is the time period between the current time and a preset time after the current time.

[0098] The calculation unit is used to calculate the feature encoding of the target object in the task layer corresponding to the target task in the task result prediction model to obtain the prediction result of the target task.

[0099] Based on the above embodiments, optionally, the coding layer in the task result prediction model includes an information coding layer, a graph coding layer, and a time series coding layer; the coding layer performs coding operations on the data in sequence according to the information coding layer, the graph coding layer, and the time series coding layer; the information coding layer is used to encode data at different times, the graph coding layer is used to encode data based on relational data, and the time series coding layer is used to encode data within a time period.

[0100] Based on the above embodiments, optionally, the encoding unit is used for:

[0101] The information encoding layer in the task result prediction model encodes the target static data and target dynamic data of each type of object to obtain the first object feature encoding corresponding to each type of object at different times.

[0102] Based on the relational data corresponding to each type of object, the graph coding layer in the task result prediction model encodes the first object feature code to obtain the second object feature code corresponding to each type of object at different times;

[0103] The time series encoding layer in the task result prediction model encodes the second object feature code within a preset time period to obtain the target object feature code corresponding to each type of target object in the preset time period for the target task. The preset time period is the time period between the current time and a preset time after the current time.

[0104] Based on the above embodiments, optionally, the task result prediction model includes a prompt word unit, which is used to store physical data related to the task in order to fine-tune the parameters of the coding layer in the task result prediction model.

[0105] The task result prediction device provided in the embodiments of the present invention can execute the task result prediction method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0106] Example 4

[0107] According to embodiments of this disclosure, this disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0108] Figure 7 A schematic diagram of an electronic device that can be used to implement the task outcome prediction method of embodiments of the present invention 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 processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0109] like Figure 7 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 may also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0110] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0111] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as task outcome prediction methods.

[0112] In some embodiments, the task outcome prediction method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the task outcome prediction method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the task outcome prediction method by any other suitable means (e.g., by means of firmware).

[0113] Various embodiments 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-a-chip (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0114] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0115] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0116] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device 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 provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, 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 sound input, voice input, or tactile input).

[0117] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0118] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0119] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0120] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for predicting task outcomes, characterized in that, The method includes: The target structure data for the target task is determined. This target structure data is derived from the actual and simulated data corresponding to the target task based on the data structure of the task result prediction model. The actual data contains data with physical meaning related to the building. The simulated data is building data generated by various building simulation software. The target structure data reflects the physical mechanism of the building. Based on the target structure data and the task result prediction model, the prediction result of the target task is obtained; The task result prediction model includes an encoding layer and at least one task layer, with the task layer following the encoding layer. The encoding layer encodes structural data and outputs object feature encodings. The task layer calculates the object feature encodings to obtain the prediction result of the target task, where each task includes at least one type of object. The encoding layer in the task result prediction model includes an information encoding layer, a graph encoding layer, and a time series encoding layer. The encoding layer performs encoding operations on the data sequentially according to the information encoding layer, graph encoding layer, and time series encoding layer. The information encoding layer encodes data at different times, the graph encoding layer encodes data based on relational data, and the time series encoding layer encodes data within a time period. The relational data describes the degree of association between different types of objects that are related. The target structure data for determining the target task includes: Obtain multi-dimensional data of the target task, including actual data and simulated data; Extract at least one type of target object from the multi-dimensional data of the target task, and extract static and dynamic data corresponding to the target object from the multi-dimensional data of the target task; the static data is data that does not change over time, and the dynamic data is data that changes over time. Based on the data structure of the task result prediction model, the static and dynamic data corresponding to at least one type of target object are integrated to determine the target relationship data, target static data, and target dynamic data of at least one type of target object corresponding to the target task. The relationship data is used to describe the degree of association between different types of objects that are related. The target static data, target dynamic data, and target relationship data are used as the target structure data of the target task.

2. The method according to claim 1, characterized in that, By integrating the static and dynamic data corresponding to at least one of the target objects, the target relationship data, target static data, and target dynamic data of at least one type of target object corresponding to the target task are determined, including: A data structure transformation table is determined for different types of objects. Based on the data structure transformation table, the static and dynamic data corresponding to the target object are transformed to obtain the target static data and target dynamic data of at least one type of object corresponding to the target task. The data structure transformation table is a data structure transformation relationship between different types of objects and their corresponding static and dynamic data established according to the data structure in the task result prediction model. A relationship list of different types of objects is determined. Based on the relationship list, static data and dynamic data corresponding to at least one type of target object, target relationship data of at least one type of target object corresponding to the target task is determined. The relationship list is used to describe different types of objects that are related, and the relationship data is used to describe the degree of association between different types of objects that are related.

3. The method according to claim 1, characterized in that, Based on the target structure data and the task result prediction model, the prediction result of the target task is obtained, including: The target structure data is input into the task result prediction model. The encoding layer in the task result prediction model encodes the target structure data to obtain the target object feature code for each type of target object corresponding to the target task in a preset time period. The preset time period is the time period between the current time and a preset time after the current time. In the task result prediction model, the task layer corresponding to the target task calculates the feature encoding of the target object to obtain the prediction result of the target task.

4. The method according to claim 1, characterized in that, The encoding layer in the task result prediction model encodes the target structure data to obtain the target object feature encoding for each type of target object corresponding to the target task within a preset time period, including: The information encoding layer in the task result prediction model encodes the target static data and target dynamic data of each type of object to obtain the first object feature encoding corresponding to each type of target object at different times; Based on the target relationship data corresponding to each type of target object, the graph coding layer in the task result prediction model encodes the first object feature code to obtain the second object feature code corresponding to each type of target object at different times; The time series encoding layer in the task result prediction model encodes the second object feature code within a preset time period to obtain the target object feature code corresponding to each type of target object in the preset time period for the target task. The preset time period is the time period between the current time and a preset time after the current time.

5. The method according to claim 1, characterized in that, The task result prediction model includes a prompt word unit, which is used to store physical data related to the task in order to fine-tune the parameters of the coding layer in the task result prediction model.

6. A task outcome prediction device, characterized in that, The device includes: The data determination module is used to determine the target structure data of the target task. The target structure data is derived from the actual data and simulated data corresponding to the target task based on the data structure of the task result prediction model. The actual data contains data with physical meaning related to the building. The simulated data is building data generated by various building simulation software. The target structure data reflects the physical mechanism of the building. The prediction module is used to obtain the prediction result of the target task based on the target structure data and the task result prediction model; The task result prediction model includes an encoding layer and at least one task layer, with the task layer following the encoding layer. The encoding layer encodes structural data and outputs object feature encodings. The task layer calculates the object feature encodings to obtain the prediction result of the target task, where each task includes at least one type of object. The encoding layer in the task result prediction model includes an information encoding layer, a graph encoding layer, and a time series encoding layer. The encoding layer performs encoding operations on the data sequentially according to the information encoding layer, graph encoding layer, and time series encoding layer. The information encoding layer encodes data at different times, the graph encoding layer encodes data based on relational data, and the time series encoding layer encodes data within a time period. The relational data describes the degree of association between different types of objects that are related. The data determination module includes: A data acquisition unit is used to acquire multi-dimensional data of the target task, including actual data and simulated data; A data extraction unit is configured to extract at least one type of target object from the multi-dimensional data of the target task, and to extract static and dynamic data corresponding to the target object from the multi-dimensional data of the target task; the static data is data that does not change over time, and the dynamic data is data that changes over time. The data integration unit is used to integrate static and dynamic data corresponding to at least one target object according to the data structure of the task result prediction model, and to determine target relationship data, target static data and target dynamic data of at least one type of object corresponding to the target task. The relationship data is used to describe the degree of association between different types of objects that are related. The target structure data combination unit is used to combine the target static data, target dynamic data and target relationship data as the target structure data of the target task.

7. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the task outcome prediction method according to any one of claims 1-5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the task result prediction method according to any one of claims 1-5.

Images