Raw material attribute prediction method and device, equipment, medium and program product

Abstract

The invention provides a raw material attribute prediction method and device, equipment, a medium and a program product. Relates to the technical field of computer application such as artificial intelligence and deep learning. Comprising the following steps: encoding and decoding a to-be-completed six-tuple consisting of raw material type information, raw material name information, raw material unit information, raw material production place information, raw material value attribute information and timestamp information to obtain a real complex number embedding vector with an existing attribute and a predicted complex number embedding vector for predicting the to-be-completed attribute; the existing attributes represent other attributes except the attributes to be complemented in the six-tuple to be complemented; according to the real complex number embedding vector and the predicted complex number embedding vector, calculating a candidate matching degree evaluation value representing the matching degree between the prediction result of the to-be-complemented attribute and the real information of the existing attribute; and according to the candidate matching degree evaluation value, determining a target result for attribute prediction to be complemented.

Description

Technical Field

[0001] The present invention relates to the field of computer application technologies, and in particular, to fields such as artificial intelligence and deep learning. More specifically, the present invention relates to a method, device, equipment, medium, and program product for predicting raw material attributes. Background Art

[0002] An important item in the economic evaluation of mines is to estimate the costs, attributes, etc. of raw materials, fuel power, etc. required for mining. When estimating them, generally, manual inquiry or speculation based on historical value attributes is used to determine, which consumes a huge amount of energy. Further, due to the rapid changes in factors such as market supply and demand, the relevant attribute information shows violent and frequent fluctuations, resulting in the inability of traditional methods to accurately calculate the attributes, directly affecting the evaluation results and investment decisions. In addition, affected by the collection accuracy and methods of data, there are certain problems such as missing and misrecording, so it is very difficult to accurately calculate the attributes. Summary of the Invention

[0003] In view of this, the present invention provides a method, device, equipment, medium, and program product for predicting raw material attributes.

[0004] One aspect of the present invention provides a method for predicting raw material attributes, including: encoding and decoding a to-be-completed six-tuple composed of raw material type information, raw material name information, raw material unit information, raw material origin information, raw material value attribute information, and timestamp information to obtain a true complex embedding vector of the existing attributes in the to-be-completed six-tuple and a predicted complex embedding vector for predicting the to-be-completed attributes in the to-be-completed six-tuple, where the to-be-completed attributes include any one of the following: raw material type information, raw material name information, raw material unit information, raw material origin information, raw material value attribute information, and the existing attributes represent other attributes in the to-be-completed six-tuple except the to-be-completed attributes; calculating a candidate matching degree evaluation value representing the matching degree between the prediction result of the to-be-completed attribute and the true information of the existing attributes according to the true complex embedding vector and the predicted complex embedding vector; and determining a target result for predicting the to-be-completed attribute according to the candidate matching degree evaluation value.

[0005] Another aspect of the present invention provides a raw material attribute prediction device, comprising: a prediction module, configured to encode and decode a to-be-completed six-tuple composed of raw material type information, raw material name information, raw material unit information, raw material origin information, raw material value attribute information, and timestamp information, to obtain a true complex embedding vector of the existing attributes in the to-be-completed six-tuple and a predicted complex embedding vector for predicting the to-be-completed attributes in the to-be-completed six-tuple, where the to-be-completed attributes include any one of the following: raw material type information, raw material name information, raw material unit information, raw material origin information, raw material value attribute information, and the existing attributes represent other attributes in the to-be-completed six-tuple except the to-be-completed attributes; a candidate matching degree evaluation value calculation module, configured to calculate a candidate matching degree evaluation value representing the matching degree between the prediction result of the to-be-completed attributes and the true information of the existing attributes according to the true complex embedding vector and the predicted complex embedding vector; and a target result determination module, configured to determine a target result for predicting the to-be-completed attributes according to the candidate matching degree evaluation value.

[0006] Another aspect of the present invention provides an electronic device, comprising: one or more processors; a memory, configured to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors are caused to implement the raw material attribute prediction method of the present invention.

[0007] Another aspect of the present invention provides a computer-readable storage medium, storing computer-executable instructions, which are used to implement the raw material attribute prediction method of the present invention when executed.

[0008] Another aspect of the present invention provides a computer program product, which includes computer-executable instructions, and the instructions are used to implement the raw material attribute prediction method of the present invention when executed. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] Through the following description of the embodiments of the present invention with reference to the drawings, the above and other objects, features, and advantages of the present invention will become clearer. In the drawings:

[0010] Figure 1 An exemplary system architecture to which the raw material attribute prediction method according to the embodiment of the present invention can be applied is shown;

[0011] Figure 2 A flowchart of the raw material attribute prediction method according to the embodiment of the present invention is shown;

[0012] Figure 3 A schematic diagram of the technical principle of the MFIA scoring function according to the embodiment of the present invention is shown;

[0013] Figure 4AShows a functional module diagram of the MFIA model according to an embodiment of the present invention;

[0014] Figure 4B Shows an overall flowchart of the process of designing and using the MFIA model according to an embodiment of the present invention;

[0015] Figure 5 Shows a block diagram of a raw material attribute prediction device according to an embodiment of the present invention;

[0016] Figure 6 Shows a block diagram of an electronic device suitable for implementing a raw material attribute prediction method according to an embodiment of the present invention. Detailed implementation manners

[0017] Hereinafter, embodiments of the present invention will be described with reference to the accompanying drawings. However, it should be understood that these descriptions are merely exemplary and are not intended to limit the scope of the present invention. In the following detailed description, for the sake of explanation, many specific details are set forth to provide a comprehensive understanding of the embodiments of the present invention. However, it is obvious that one or more embodiments can also be implemented without these specific details. In addition, in the following description, descriptions of well-known structures and technologies are omitted to avoid unnecessarily confusing the concepts of the present invention.

[0018] The terms used herein are merely for describing specific embodiments and are not intended to limit the present invention. The terms "including", "comprising" and the like used herein indicate the presence of the described features, steps, operations and / or components, but do not exclude the presence or addition of one or more other features, steps, operations or components.

[0019] All terms used herein (including technical and scientific terms) have the meanings commonly understood by those skilled in the art, unless otherwise defined. It should be noted that the terms used herein should be interpreted as having a meaning consistent with the context of this specification and should not be interpreted in an idealized or overly rigid manner.

[0020] In the case of using expressions such as "at least one of A, B, and C", generally, it should be interpreted according to the meaning commonly understood by those skilled in the art (for example, "a system having at least one of A, B, and C" should include, but not be limited to, a system having only A, only B, only C, having A and B, having A and C, having B and C, and / or having A, B, and C).

[0021] In the embodiments of the present invention, in aspects such as the collection, update, analysis, processing, use, transmission, provision, disclosure, and storage of the involved data (for example, including but not limited to user personal information), it complies with the provisions of relevant laws and regulations, is used for legal purposes, and does not violate public order and good customs. In particular, necessary measures are taken for user personal information to prevent illegal access to user personal information data and maintain information security.

[0022] Figure 1 FIG. shows an exemplary system architecture to which the raw material attribute prediction method according to an embodiment of the present invention can be applied. It should be noted that, Figure 1 What is shown is only an example of the system architecture to which the embodiments of the present invention can be applied, to help those skilled in the art understand the technical content of the present invention, but it does not mean that the embodiments of the present invention cannot be used in other devices, systems, environments or scenarios.

[0023] As Figure 1 shown, the system architecture 100 according to this embodiment may include a first terminal device 101, a second terminal device 102, a third terminal device 103, a network 104, and a server 105. The network 104 is used to provide a medium for communication links between the first terminal device 101, the second terminal device 102, the third terminal device 103, and the server 105. The network 104 may include various connection types, such as wired and / or wireless communication links, etc.

[0024] Users can use the first terminal device 101, the second terminal device 102, and the third terminal device 103 to interact with the server 105 through the network 104 to receive or send messages, etc. Various communication client applications may be installed on the first terminal device 101, the second terminal device 102, and the third terminal device 103, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, and / or social platform software, etc. (only as examples).

[0025] The first terminal device 101, the second terminal device 102, and the third terminal device 103 may be various electronic devices with a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop portable computers, and desktop computers, etc.

[0026] The server 105 may be a server providing various services, such as a background management server that supports the websites browsed by users using the first terminal device 101, the second terminal device 102, and the third terminal device 103 (only as an example). The background management server may analyze and process data such as received user requests, and feedback the processing results (such as web pages, information, or data obtained or generated according to user requests) to the terminal device.

[0027] It should be noted that the raw material attribute prediction method provided by the embodiments of the present invention can generally be executed by the server 105. Correspondingly, the raw material attribute prediction device provided by the embodiments of the present invention can generally be set in the server 105. The raw material attribute prediction method provided by the embodiments of the present invention can also be executed by a server or a server cluster different from the server 105 and capable of communicating with the first terminal device 101, the second terminal device 102, the third terminal device 103, and / or the server 105. Correspondingly, the raw material attribute prediction device provided by the embodiments of the present invention can also be set in a server or a server cluster different from the server 105 and capable of communicating with the first terminal device 101, the second terminal device 102, the third terminal device 103, and / or the server 105. Alternatively, the raw material attribute prediction method provided by the embodiments of the present invention can also be executed by the first terminal device 101, the second terminal device 102, or the third terminal device 103, or can also be executed by other terminal devices different from the first terminal device 101, the second terminal device 102, or the third terminal device 103. Correspondingly, the raw material attribute prediction device provided by the embodiments of the present invention can also be set in the first terminal device 101, the second terminal device 102, or the third terminal device 103, or can be set in other terminal devices different from the first terminal device 101, the second terminal device 102, or the third terminal device 103.

[0028] For example, the six-tuple to be completed can be originally stored in any one of the first terminal device 101, the second terminal device 102, or the third terminal device 103 (for example, the first terminal device 101, but not limited thereto), or stored on an external storage device and can be imported into the first terminal device 101. Then, the first terminal device 101 can execute the raw material attribute prediction method provided by the embodiments of the present invention locally, or send the six-tuple to be completed to other terminal devices, servers, or server clusters, and the raw material attribute prediction method provided by the embodiments of the present invention is executed by the other terminal devices, servers, or server clusters that receive the six-tuple to be completed.

[0029] It should be understood that Figure 1 the numbers of terminal devices, networks, and servers in

[0030] Figure 2 FIG. shows a flowchart of the raw material attribute prediction method according to an embodiment of the present invention.

[0031] As Figure 2 shown, the method includes operations S201 to S203.

[0032] In operation S201, encode and decode a six - tuple to be completed, which consists of raw material type information, raw material name information, raw material unit information, raw material origin information, raw material value attribute information, and timestamp information, to obtain the true complex embedding vectors of the existing attributes in the six - tuple to be completed and the predicted complex embedding vectors for the attributes to be completed in the six - tuple to be completed. The attributes to be completed include any one of the following: raw material type information, raw material name information, raw material unit information, raw material origin information, raw material value attribute information. The existing attributes represent the other attributes in the six - tuple to be completed except for the attributes to be completed.

[0033] According to an embodiment of the present invention, in the raw material attribute prediction scenario, the six - tuple used can be expressed as (raw material type, raw material name, raw material unit, raw material origin, raw material value attribute, timestamp). Using a null value (NULL) to represent the attribute to be completed in the six - tuple, the six - tuple to be completed can be expressed as (NULL, raw material name, raw material unit, raw material origin, raw material value attribute, timestamp), (raw material type, NULL, raw material unit, raw material origin, raw material value attribute, timestamp), (raw material type, raw material name, NULL, raw material origin, raw material value attribute, timestamp), (raw material type, raw material name, raw material unit, NULL, raw material value attribute, timestamp), (raw material type, raw material name, raw material unit, raw material origin, NULL, timestamp), etc.

[0034] According to an embodiment of the present invention, encoding and decoding are mainly used to encode relevant attribute information into complex embedding vectors for representation. The encoding and decoding process can adopt various encoding and decoding modules that can encode and decode information into complex embedding vectors, which are not limited herein.

[0035] For example, in the raw material value attribute prediction scenario, the six - tuple to be completed can be (raw material type, raw material name, raw material unit, raw material origin, NULL, timestamp). In this case, by encoding the raw material type, raw material name, raw material unit, raw material origin, and timestamp respectively, the true complex embedding vectors determined by the raw material type complex embedding vector, raw material name complex embedding vector, raw material unit complex embedding vector, raw material origin complex embedding vector, and timestamp complex embedding vector can be obtained. Then, by encoding and decoding the raw material type complex embedding vector, raw material name complex embedding vector, raw material unit complex embedding vector, raw material origin complex embedding vector, and timestamp complex embedding vector, the raw material value attribute complex embedding vector can be predicted as the prediction result for NULL in (raw material type, raw material name, raw material unit, raw material origin, NULL, timestamp).

[0036] In operation S202, based on the real complex embedding vector and the predicted complex embedding vector, a candidate matching degree evaluation value is calculated, which represents the matching degree between the predicted result of the attribute to be completed and the real information of the existing attributes.

[0037] According to an embodiment of the present invention, the predicted result can be determined according to the existing results in the six-tuple dataset. The six-tuple dataset can represent a set of six-tuple data obtained by collecting and structuring the historical data information of raw materials. The predicted result can have one or more. Each predicted result can have a corresponding candidate matching degree evaluation value.

[0038] In operation S203, based on the candidate matching degree evaluation value, the target result predicted for the attribute to be completed is determined.

[0039] According to an embodiment of the present invention, a preset threshold can be set in advance, and the target result is determined according to the predicted result corresponding to the candidate matching degree evaluation value greater than the preset threshold. In the case where there is no candidate matching degree evaluation value greater than the preset threshold, no result or an error message can be output.

[0040] Through the above embodiments of the present invention, by encoding and decoding relevant attributes into complex embedding vectors, the problem of raw material attribute calculation and data loss can be deeply analyzed based on the powerful representation ability of the complex space, improving the accuracy of raw material attribute calculation, further improving the scientific nature of economic evaluation, and making progress in improving the level of mine economic evaluation work.

[0041] The following combines specific embodiments to Figure 2 further illustrate the

[0042] According to an embodiment of the present invention, the above operation S201 may include: performing one-hot encoding on the existing attributes to obtain an existing attribute binary vector. Performing complex conversion on the existing attribute binary vector to obtain a real complex embedding vector. Performing encoding and decoding on the real complex embedding vector to obtain a predicted complex embedding vector.

[0043] According to an embodiment of the present invention, in the case of obtaining six-tuple data, one-hot encoding can also be first performed on the relevant attribute information in the six-tuple data. Specifically, the relevant attributes in the six-tuple data can be represented as a one-hot encoded binary vector of f dimensions, making the i-th element equal to 1 and the other elements set to 0, then the one-hot encoding process ends. After that, complex embedding encoding is performed on the one-hot encoded result to obtain the complex embedding vector of the relevant attribute.

[0044] For example, in the scenario of predicting the value attributes of raw materials, one-hot encoding can be first performed on the raw material type information, raw material name information, raw material unit information, raw material origin information, and timestamp information to obtain the raw material type binary vector, raw material name binary vector, raw material unit binary vector, raw material origin binary vector, and timestamp binary vector. Then, the raw material type binary vector, raw material name binary vector, raw material unit binary vector, raw material origin binary vector, and timestamp binary vector can be subjected to complex number conversion to obtain the raw material type complex embedding vector, raw material name complex embedding vector, raw material unit complex embedding vector, raw material origin complex embedding vector, and timestamp complex embedding vector. After that, the raw material type complex embedding vector, raw material name complex embedding vector, raw material unit complex embedding vector, raw material origin complex embedding vector, and timestamp complex embedding vector can be encoded and decoded to obtain the raw material value attribute complex embedding vector.

[0045] According to an embodiment of the present invention, corresponding to the above raw material value attribute prediction scenario, the above operation S202 may include: calculating a first matching degree evaluation value between the raw material value attribute prediction result and the raw material type information, raw material name information, raw material unit information, raw material origin information, and timestamp information according to the raw material type complex embedding vector, raw material name complex embedding vector, raw material unit complex embedding vector, raw material origin complex embedding vector, timestamp complex embedding vector, and raw material value attribute complex embedding vector. Calculating a second matching degree evaluation value between the raw material category information and the raw material unit-value attribute information according to the raw material type complex embedding vector, raw material name complex embedding vector, raw material unit complex embedding vector, raw material value attribute complex embedding vector, and timestamp complex embedding vector. Calculating a candidate matching degree evaluation value according to at least one of the first matching degree evaluation value and the second matching degree evaluation value.

[0046] According to an embodiment of the present invention, the raw material category information may represent the concatenated information obtained by concatenating the raw material type information and the raw material name information. The raw material unit-value attribute information may represent the concatenated information obtained by concatenating the raw material unit information and the raw material value attribute information.

[0047] According to an embodiment of the present invention, based on the existing complex embedding vectors, a suitable matching degree calculation method can be set according to business requirements to calculate the first matching degree evaluation value and the second matching degree evaluation value, which are not limited here. Based on obtaining the first matching degree evaluation value and the second matching degree evaluation value, a suitable calculation method can also be set according to business requirements to calculate the candidate matching degree evaluation value, which is not limited here.

[0048] According to an embodiment of the present invention, the process of calculating the first matching degree evaluation value may include: using the Hermitian operator to calculate the origin-timestamp interaction complex embedding vector between the raw material origin complex embedding vector and the timestamp unit complex embedding vector obtained by normalizing the timestamp complex embedding vector. Using the Hermitian operator to calculate the category-origin-timestamp interaction complex embedding vector between the raw material category complex embedding vector obtained by concatenating the raw material type complex embedding vector and the raw material name complex embedding vector and the origin-timestamp interaction unit complex embedding vector obtained by normalizing the origin-timestamp interaction complex embedding vector. Calculating a first difference between the first argument of the category-origin-timestamp interaction complex embedding vector and the second argument of the raw material unit-value attribute complex embedding vector obtained by concatenating the raw material unit complex embedding vector and the raw material value attribute complex embedding vector; calculating a second difference between the first absolute value of the category-origin-timestamp interaction complex embedding vector and the second absolute value of the raw material unit-value attribute complex embedding vector; performing an exponential calculation on the first difference and the second difference to obtain the first matching degree evaluation value.

[0049] In the raw material value attribute prediction scenario, for example, the raw material type complex embedding vector and the raw material name complex embedding vector can be concatenated first, and the concatenated raw material category complex embedding vector is named . The raw material unit complex embedding vector and the raw material value attribute complex embedding vector are concatenated, and the concatenated raw material unit-value attribute complex embedding vector is named .

[0050] Furthermore, in combination with formula (1), the timestamp complex embedding vector is divided by its norm to obtain the timestamp unit complex embedding vector .

[0051] (1)

[0052] where represents the norm.

[0053] Next, in combination with formula (2), the interaction between the origin and is realized by using the Hermitian operator:

[0054] (2)

[0055] where represents the Hermitian operator, and represents the origin-timestamp interaction complex embedding vector.

[0056] Then, the origin - timestamp interaction complex embedding vector can be converted into an origin - timestamp interaction unit complex embedding vector . Subsequently, in combination with formula (3), the Hermitian operator can be used to achieve and the interaction between them:

[0057] (3)

[0058] wherein, represents the category - origin - timestamp interaction complex embedding vector

[0059] Finally, through the composite error metric of complex numbers, the approximate feature interaction module scoring function for calculating the first matching degree evaluation value can be defined in the form shown in formula (4).

[0060] (4)

[0061] wherein, represents the argument of the complex number, represents the absolute value, represents the first matching degree evaluation value

[0062] According to an embodiment of the present invention, the process of calculating the second matching degree evaluation value may include: calculating the category - timestamp interaction complex embedding vector between the raw material category complex embedding vector and the timestamp unit complex embedding vector by using the Hermitian operator. Calculating the unit - value attribute - timestamp interaction complex embedding vector between the raw material unit - value attribute complex embedding vector and the timestamp unit complex embedding vector by using the Hermitian operator. Calculating the third argument of the result of the Hermitian operator between the preset dependence factor and the category - timestamp interaction complex embedding vector. Performing an exponential calculation on the difference between the third absolute value of the third argument and the fourth absolute value of the fourth argument of the unit - value attribute - timestamp interaction complex embedding vector to obtain the second matching degree evaluation value

[0063] In the raw material value attribute prediction scenario, for example, first, in combination with formula (5), a Hermitian operator can be performed between and to achieve the interaction and obtain the category - timestamp interaction complex embedding vector .

[0064] (5)

[0065] Furthermore, in combination with formula (6), between and Implement interaction by using a Hermitian operator between them to obtain a unit-value attribute-timestamp interaction complex embedding vector 。

[0066] (6)

[0067] Furthermore, a preset dependence factor collect and the difference granularities at different times at the same moment to obtain a time-series feature dependence module scoring function for calculating a second matching degree evaluation value. The time-series feature dependence module scoring function can be defined as shown in formula (7).

[0068] (7)

[0069] wherein represents the second matching degree evaluation value

[0070] According to an embodiment of the present invention, a mine multi-feature cross learning (Multi-Feature Interaction and Aggregation, abbreviated as MFIA) scoring function for calculating a candidate matching degree evaluation value can be determined according to an approximate feature interaction module scoring function and a time-series feature dependence module scoring function. For example, it can be expressed in the form shown in formula (8).

[0071] (8)

[0072] Figure 3 shows a schematic diagram of the technical principle of the MFIA scoring function according to an embodiment of the present invention

[0073] As Figure 3 shown, the technical principles of the above formulas (2) to (3) can be described in the virtual box 310. The technical principle of the above formula (4) can be described in the virtual box 320. The technical principles of the above formulas (5) to (7) can be described in the virtual box 330. The technical principle of the above formula (8) can be described in the virtual box 340

[0074] It should be noted that the above embodiments only describe the calculation method of the MFIA scoring function for the raw material value attribute prediction scenario. In other scenarios, such as the raw material type prediction scenario, the raw material name prediction scenario, the raw material unit prediction scenario, and the raw material origin prediction scenario, an MFIA scoring function applicable to the corresponding scenario can be constructed based on a method similar to the aforementioned raw material value attribute prediction scenario, as long as it is ensured that the complex embedding vector on the right side of equation (4) includes the complex embedding vector of the to-be-complemented attribute for the to-be-complemented attribute prediction. For example, it can be the complex embedding vector of the to-be-complemented attribute itself, or it can be a concatenated complex embedding vector obtained by concatenating the complex embedding vector of the to-be-complemented attribute and other real complex embedding vectors, which is not limited herein.

[0075] The design methods for other scenarios will not be elaborated herein.

[0076] Through the above embodiments of the present invention, the powerful representation ability of the complex space can be utilized to construct a multi-feature cross-learning technology, improving the accuracy of raw material attribute calculation, further enhancing the scientific nature of economic evaluation, and making progress in improving the level of mine economic evaluation work.

[0077] According to an embodiment of the present invention, in the case where there are multiple prediction results, the above operation S202 may include: calculating a candidate matching degree evaluation value between each prediction result and the real information according to each prediction complex embedding vector and the real complex embedding vector, to obtain a plurality of candidate matching degree evaluation values. On this basis, the above operation S203 may include: determining the prediction result corresponding to the candidate matching degree evaluation value with the largest value among the plurality of candidate matching degree evaluation values as the target result.

[0078] For example, for each given to-be-complemented six-tuple, the trained multi-feature cross-learning perception technology can be used to calculate the MFIA scoring function, and the prediction result with the highest calculated score is automatically recognized as the target result for complementing the to-be-complemented attribute.

[0079] According to an embodiment of the present invention, to implement the above raw material attribute prediction method, an MFIA model applicable to implementing the raw material attribute prediction method for mine technical and economic evaluation based on complex numbers can be constructed and trained based on the above MFIA scoring function.

[0080] Figure 4A The functional module diagram of the MFIA model according to an embodiment of the present invention is shown.

[0081] Such as Figure 4AAs shown in the figure, the MFIA model 400 includes a raw material attribute data import module 420, a data preprocessing module 430, an attribute prediction module 440, and a system security maintenance module 450. Among them, the data preprocessing module 430 may include a missing value processing sub-module 431, an outlier detection sub-module 432, a data normalization sub-module 433, and a data structuring sub-module 434.

[0082] Figure 4B The overall flowchart of the process of designing and using the MFIA model according to an embodiment of the present invention is shown.

[0083] As Figure 4B shown, this process includes operations S401 to S410.

[0084] In operation S401, the raw material attribute data file to be estimated is imported and stored in the database.

[0085] For example, in combination with the raw material attribute data import module 420, by clicking "Import Raw Material Attribute Data" on the page, selecting the required data file to be imported in the folder, and clicking "Upload", the import operation can be completed.

[0086] In operation S402, the data file is preprocessed to obtain a structured data set.

[0087] This operation can be performed in combination with the data preprocessing module 430, including: missing value processing, outlier detection, data normalization, and data normalization. Among them, for missing value processing, in combination with the missing value processing sub-module 431, the selected data set in the database is read, and the imported data is filled with the mean value to fill the missing raw material attribute data. For outlier detection, in combination with the outlier detection sub-module 432, statistical methods such as the interquartile range (IQR) are used to detect abnormal data and perform reasonable processing. For data normalization, in combination with the data normalization sub-module 433, the data is normalized or standardized to improve the model convergence speed. For data structuring, in combination with the data structuring sub-module 434, the Language Technology Platform (LTP) is used to perform entity extraction, relationship extraction, and entity unification on the data set in sequence. Entity extraction, that is, the recognition of entities, includes the detection and classification of entities. Feature extraction, generally, can be understood as the extraction of multi-tuples, that is, a data set can be represented in the form of a six-tuple (raw material type, raw material name, raw material unit, raw material origin, raw material value attribute, timestamp). Entity unification, such as "coal" and "lignite", needs to be unified.

[0088] In operation S403, the data set is split into a training set, a validation set, and a test set.

[0089] For example, it can be divided into a training set T, a validation set V, and a test set S in the ratio of 6:1:3. Among them, the training set is used for model training to ensure data diversity and improve generalization ability. The validation set is used to adjust hyperparameters to prevent overfitting. The test set is used for the final evaluation of the model's completion effect.

[0090] In operation S404, the data set is encoded.

[0091] In this operation, the encoding can include two stages: categorical variable processing and numerical feature transformation, or it can only include the numerical feature transformation stage. In the categorical variable processing stage, one-hot encoding can be used to obtain a binary vector. In the numerical feature transformation stage, a logarithmic transformation can be performed on the numerical variables to convert the binary vector into a four-element embedding vector.

[0092] In operation S405, a complex-based MFIA model is constructed, and the model includes a scoring function and a loss function.

[0093] In operation S406, the model hyperparameters are set.

[0094] The hyperparameters can include the initial learning rate of the model, batch size, ent_vec_dim, rel_vec_di, etc., as shown in Table 1, and are not limited to this.

[0095] Table 1:

[0096]

[0097] In operation S407, training is performed using the training set until the model loss function converges.

[0098] For example, the MFIA model can be trained using the training set data, and the parameters can be optimized through backpropagation, including: using the Adam optimization algorithm to adjust the model weights; monitoring the downward trend of the loss function to prevent gradient disappearance or explosion; evaluating the model on the validation set and adjusting the hyperparameters according to the results to ensure the generalization ability of the model.

[0099] Specifically, for a given training set T, the loss function is used to calculate the loss of the training set data until the loss function of the model converges, and then the model training is completed. The loss function can be as shown in formula (9).

[0100] (9)

[0101] Among them, is the probability vector for model prediction, is the label vector, which is set to 1 for the true six-tuple and 0 for the predicted six-tuple, is the loss function. denotes the th six-tuple. is the total number of six-tuples. denotes a real-valued embedding vector of dimension denotes the total number of entities of the six types of entities characterized in the six-tuple determined by (raw material type, raw material name, raw material unit, raw material origin, raw material value attribute, timestamp).

[0102] In operation S408, the trained MFIA model is used to complete the test data set.

[0103] This operation can be performed in combination with the attribute prediction module 440, including: data entering the model, the scoring function calculating the score, and the higher the score, the closer it is to the deduced attribute. All data in the test set are traversed to complete the deduction of the test set.

[0104] In operation S409, the attribute deduction results are visually displayed.

[0105] In operation S410, the effect of the MFIA model is evaluated and verified through experiments.

[0106] For example, the error between the predicted data and the true data can be calculated to evaluate the accuracy of the completion; the completed data can be recorded and compared with existing methods. Specifically, the mean absolute error (MAE), root mean square error (RMSE), and Pearson correlation coefficient (CC) of the experiment can be calculated to evaluate the effect of the model. To better balance these three indicators, a comparative experiment can be adopted to evaluate and verify the performance of the technology.

[0107] The summary table of test evaluation indicators is shown in Table 2, which shows the comparison results between MFIA and Decision Tree (DT) model, Autoregressive Model (AR), Support Vector Regression with Polynomial Kernel (SVR-POLY) model, Support Vector Regression with Radial Basis Function Kernel (SVR-RBF) model, Support Vector Regression with Linear Kernel (SVR-LINEAR) model, Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), Convolutional Neural Network + Long Short-Term Memory (CNN+LSTM), Convolutional Neural Network + Gated Recurrent Unit (CNN+GRU), and Empirical Mode Decomposition (EMD) model.

[0108] Table 2:

[0109]

[0110] During the entire process of the above operations S401~S410, real-time maintenance can be combined with the system security maintenance module 450.

[0111] Through the above embodiments of the present invention, an intelligent calculation method for the attributes of raw materials in mine technical and economic evaluation is provided. This method is based on the complex space and uses the Hermitian operator to interact different features. In addition, by using the potential dependence factor, different time difference granularities of different complex embedding vectors are collected at the same time. Finally, the reasonable calculation of the raw material attributes is realized, and the results are presented visually through the web (Web). Compared with other methods, this method can calculate the attributes of mine raw materials with higher efficiency and high interpretability through the powerful accommodation ability of the complex space, making the cost estimation of mine economic evaluation more accurate. This method introduces mathematical principles into the system application and presents it in a black box manner. The system interface is simple and beautiful, and there are no technical requirements for operators.

[0112] Figure 5 The block diagram of a raw material attribute prediction device according to an embodiment of the present invention is shown.

[0113] As Figure 5 shown, the raw material attribute prediction 500 includes a prediction module 510, a candidate matching degree evaluation value calculation module 520, and a target result determination module 530.

[0114] The prediction module 510 is configured to encode and decode a to-be-completed six-tuple composed of raw material type information, raw material name information, raw material unit information, raw material origin information, raw material value attribute information, and timestamp information, to obtain a true complex embedding vector of the existing attributes in the to-be-completed six-tuple and a predicted complex embedding vector predicted for the to-be-completed attributes in the to-be-completed six-tuple. The to-be-completed attributes include any one of the following: raw material type information, raw material name information, raw material unit information, raw material origin information, raw material value attribute information, and the existing attributes represent other attributes in the to-be-completed six-tuple except the to-be-completed attributes.

[0115] The candidate matching degree evaluation value calculation module 520 is configured to calculate a candidate matching degree evaluation value representing the matching degree between the prediction result of the to-be-completed attribute and the true information of the existing attributes according to the true complex embedding vector and the predicted complex embedding vector.

[0116] The target result determination module 530 is configured to determine the target result predicted for the to-be-completed attribute according to the candidate matching degree evaluation value.

[0117] According to an embodiment of the present invention, the to-be-completed attribute is an attribute representing raw material value attribute information, the prediction result is the raw material value attribute prediction result, and the true complex embedding vector is the raw material type complex embedding vector, the raw material name complex embedding vector, the raw material unit complex embedding vector, the raw material origin complex embedding vector, and the timestamp complex embedding vector. The predicted complex embedding vector is the raw material value attribute complex embedding vector.

[0118] According to an embodiment of the present invention, the candidate matching degree evaluation value calculation module includes a first matching degree evaluation value calculation unit, a second matching degree evaluation value calculation unit, and a first candidate matching degree evaluation value calculation unit.

[0119] The first matching degree evaluation value calculation unit is configured to calculate a first matching degree evaluation value between the raw material value attribute prediction result and the raw material type information, the raw material name information, the raw material unit information, the raw material origin information, and the timestamp information according to the raw material type complex embedding vector, the raw material name complex embedding vector, the raw material unit complex embedding vector, the raw material origin complex embedding vector, the timestamp complex embedding vector, and the raw material value attribute complex embedding vector.

[0120] A second matching degree evaluation value calculation unit, which is configured to calculate a second matching degree evaluation value between the raw material category information and the raw material unit-value attribute information according to the raw material type plural embedding vectors, the raw material name plural embedding vectors, the raw material unit plural embedding vectors, the raw material value attribute plural embedding vectors, and the timestamp plural embedding vectors.

[0121] A first candidate matching degree evaluation value calculation unit, which is configured to calculate a candidate matching degree evaluation value according to at least one of the first matching degree evaluation value and the second matching degree evaluation value.

[0122] According to an embodiment of the present invention, the first matching degree evaluation value calculation unit includes a first Hermitian operator subunit, a second Hermitian operator subunit, a first difference calculation subunit, a second difference calculation subunit, and a first exponential calculation subunit.

[0123] The first Hermitian operator subunit is configured to use the Hermitian operator to calculate a production area-timestamp interaction complex embedding vector between the raw material production area plural embedding vectors and the timestamp unit complex embedding vector obtained by normalizing the timestamp plural embedding vectors.

[0124] The second Hermitian operator subunit is configured to use the Hermitian operator to calculate a category-production area-timestamp interaction complex embedding vector between the raw material category complex embedding vector obtained by splicing the raw material type plural embedding vectors and the raw material name plural embedding vectors and the production area-timestamp interaction unit complex embedding vector obtained by normalizing the production area-timestamp interaction complex embedding vector.

[0125] The first difference calculation subunit is configured to calculate a first difference between the first argument of the category-production area-timestamp interaction complex embedding vector and the second argument of the raw material unit-value attribute complex embedding vector obtained by splicing the raw material unit plural embedding vectors and the raw material value attribute plural embedding vectors.

[0126] The second difference calculation subunit is configured to calculate a second difference between the first absolute value of the category-production area-timestamp interaction complex embedding vector and the second absolute value of the raw material unit-value attribute complex embedding vector.

[0127] The first exponential calculation subunit is configured to perform an exponential calculation on the first difference and the second difference to obtain the first matching degree evaluation value.

[0128] According to an embodiment of the present invention, the second matching degree evaluation value calculation unit includes a third Hermitian operator subunit, a fourth Hermitian operator subunit, a fifth Hermitian operator subunit, and a second exponential calculation subunit.

[0129] The third Hermitian operator subunit is used to calculate the category - timestamp interaction complex embedding vector between the raw material category complex embedding vector and the timestamp unit complex embedding vector by using the Hermitian operator.

[0130] The fourth Hermitian operator subunit is used to calculate the unit - value attribute - timestamp interaction complex embedding vector between the raw material unit - value attribute complex embedding vector and the timestamp unit complex embedding vector by using the Hermitian operator. The fifth Hermitian operator subunit is used to calculate the third argument of the result of the Hermitian operator calculation between the preset dependence factor and the category - timestamp interaction complex embedding vector.

[0131] The second exponential calculation subunit is used to perform an exponential calculation on the difference between the third absolute value of the third argument and the fourth absolute value of the fourth argument of the unit - value attribute - timestamp interaction complex embedding vector to obtain the second matching degree evaluation value.

[0132] According to an embodiment of the present invention, the prediction module includes a one - hot encoding unit, a complex number conversion unit, and an encoding - decoding unit.

[0133] The one - hot encoding unit is used to perform one - hot encoding on the existing attributes to obtain an existing attribute binary vector.

[0134] The complex number conversion unit is used to perform complex number conversion on the existing attribute binary vector to obtain a real complex embedding vector.

[0135] The encoding - decoding unit is used to perform encoding - decoding on the real complex embedding vector to obtain a predicted complex embedding vector.

[0136] According to an embodiment of the present invention, there are multiple prediction results. The candidate matching degree evaluation value calculation module includes a second candidate matching degree evaluation value calculation unit.

[0137] The second candidate matching degree evaluation value calculation unit is used to calculate the candidate matching degree evaluation value between each prediction result and the real information according to each predicted complex embedding vector and the real complex embedding vector, and obtain multiple candidate matching degree evaluation values.

[0138] The target result determination module includes a target result determination unit.

[0139] The target result determination unit is used to determine the prediction result corresponding to the candidate matching degree evaluation value with the largest value among the multiple candidate matching degree evaluation values calculated as the target result.

[0140] Any of a plurality of modules, units, and subunits according to an embodiment of the present invention, or at least part of the functions of any of them, may be implemented in one module. Any one or more of the modules, units, and subunits according to an embodiment of the present invention may be split into multiple modules for implementation. Any one or more of the modules, units, and subunits according to an embodiment of the present invention may be at least partially implemented as a hardware circuit, such as a field-programmable gate array (FPGA), a programmable logic array (PLA), a system-on-chip, a system-on-substrate, a system-on-package, an application-specific integrated circuit (ASIC), or may be implemented by any other reasonable way of integrating or packaging circuits, or implemented in any one of the three implementation manners of software, hardware, and firmware, or in any appropriate combination of several of them. Alternatively, one or more of the modules, units, and subunits according to an embodiment of the present invention may be at least partially implemented as a computer program module, which can perform corresponding functions when the computer program module is run.

[0141] For example, any of the prediction module 510, the candidate matching degree evaluation value calculation module 520, and the target result determination module 530 may be combined and implemented in one module / unit / subunit, or any one of the module / unit / subunit may be split into multiple module / unit / subunits. Alternatively, at least part of the functions of one or more of these module / unit / subunits may be combined with at least part of the functions of other module / unit / subunits and implemented in one module / unit / subunit. According to an embodiment of the present invention, at least one of the prediction module 510, the candidate matching degree evaluation value calculation module 520, and the target result determination module 530 may be at least partially implemented as a hardware circuit, such as a field-programmable gate array (FPGA), a programmable logic array (PLA), a system-on-chip, a system-on-substrate, a system-on-package, an application-specific integrated circuit (ASIC), or may be implemented by any other reasonable way of integrating or packaging circuits, or implemented in any one of the three implementation manners of software, hardware, and firmware, or in any appropriate combination of several of them. Alternatively, at least one of the prediction module 510, the candidate matching degree evaluation value calculation module 520, and the target result determination module 530 may be at least partially implemented as a computer program module, which can perform corresponding functions when the computer program module is run.

[0142] Figure 6 The block diagram of an electronic device suitable for implementing the raw material property prediction method according to an embodiment of the present invention is shown. Figure 6 The shown electronic device is only an example and should not impose any limitation on the functions and usage scope of the embodiments of the present invention.

[0143] As Figure 6As shown, an electronic device 600 according to an embodiment of the present invention includes a processor 601, which can perform various appropriate actions and processes according to programs stored in a read-only memory (ROM) 602 or programs loaded from a storage section 608 into a random access memory (RAM) 603. The processor 601 may include, for example, a general-purpose microprocessor (such as a CPU), an instruction set processor, and / or a related chipset, and / or a dedicated microprocessor (such as an application-specific integrated circuit (ASIC)), and so on. The processor 601 may also include on-board memory for caching purposes. The processor 601 may include a single processing unit or multiple processing units for performing different actions of a method flow according to an embodiment of the present invention.

[0144] In the RAM 603, various programs and data required for the operation of the electronic device 600 are stored. The processor 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. The processor 601 performs various operations of a method flow according to an embodiment of the present invention by executing programs in the ROM 602 and / or the RAM 603. It should be noted that the programs may also be stored in one or more memories other than the ROM 602 and the RAM 603. The processor 601 may also perform various operations of a method flow according to an embodiment of the present invention by executing programs stored in the one or more memories.

[0145] According to an embodiment of the present invention, the electronic device 600 may further include an input / output (I / O) interface 605, and the input / output (I / O) interface 605 is also connected to the bus 604. The system 600 may further include one or more of the following components connected to the input / output (I / O) interface 605: an input section 606 including a keyboard, a mouse, etc.; an output section 607 including, for example, a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 608 including a hard disk, etc.; and a communication section 609 including a network interface card such as a LAN card, a modem, etc. The communication section 609 performs communication processing via a network such as the Internet. A drive 610 is also connected to the input / output (I / O) interface 605 as needed. A removable medium 611, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 610 as needed so that a computer program read from it can be installed into the storage section 608 as needed.

[0146] According to an embodiment of the present invention, the method flow according to the embodiment of the present invention can be implemented as a computer software program. For example, an embodiment of the present invention includes a computer program product, which includes a computer program carried on a computer-readable storage medium, and the computer program contains program codes for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through the communication part 609, and / or installed from the removable medium 611. When the computer program is executed by the processor 601, the above functions defined in the system of the embodiment of the present invention are executed. According to an embodiment of the present invention, the above-described systems, devices, apparatuses, modules, units, etc. can be implemented by computer program modules.

[0147] The present invention also provides a computer-readable storage medium, which can be included in the device / device / system described in the above embodiment; or can exist alone without being assembled into the device / device / system. The above computer-readable storage medium carries one or more programs, and when the above one or more programs are executed, the method according to the embodiment of the present invention is implemented.

[0148] According to an embodiment of the present invention, the computer-readable storage medium can be a non-volatile computer-readable storage medium. For example, it can include but is not limited to: portable computer disks, hard disks, random access memories (RAMs), read-only memories (ROMs), erasable programmable read-only memories (EPROMs or flash memories), portable compact disk read-only memories (CD-ROMs), optical storage devices, magnetic storage devices, or any suitable combination of the above. In the present invention, the computer-readable storage medium can be any tangible medium that contains or stores a program, and the program can be used by or in combination with an instruction execution system, device, or device.

[0149] For example, according to an embodiment of the present invention, the computer-readable storage medium can include the above-described ROM 602 and / or RAM 603 and / or one or more memories other than ROM 602 and RAM 603.

[0150] An embodiment of the present invention also includes a computer program product, which includes a computer program, and the computer program contains program codes for executing the method provided by the embodiment of the present invention. When the computer program product runs on an electronic device, the program codes are used to enable the electronic device to implement the raw material attribute prediction method provided by the embodiment of the present invention.

[0151] When the computer program is executed by the processor 601, the above functions defined in the system / device of the embodiment of the present invention are executed. According to an embodiment of the present invention, the above-described systems, devices, modules, units, etc. can be implemented by computer program modules.

[0152] In one embodiment, the computer program may rely on tangible storage media such as optical storage devices and magnetic storage devices. In another embodiment, the computer program may also be transmitted and distributed in the form of signals on a network medium, and downloaded and installed through the communication section 609, and / or installed from the removable medium 611. The program code included in the computer program can be transmitted using any suitable network medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0153] According to an embodiment of the present invention, the program code for executing the computer program provided by the embodiments of the present invention can be written in any combination of one or more programming languages. Specifically, these computing programs can be implemented using high-level procedures and / or object-oriented programming languages, and / or assembly / machine languages. Programming languages include but are not limited to, for example, Java, C++, Python, the "C" language, or similar programming languages. The program code can be executed entirely on the user's computing device, partially on the user's device, partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computing device (e.g., by connecting through the Internet using an Internet service provider).

[0154] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagram may represent a module, a segment of a program, or a part of code that contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than that marked in the accompanying drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram or flowchart, as well as combinations of blocks in the block diagram or flowchart, can be implemented by a dedicated hardware-based system that performs the specified functions or operations, or can be implemented by a combination of dedicated hardware and computer instructions. Those skilled in the art can understand that the features recited in the various embodiments and / or claims of the present invention can be combined and / or combined in various ways, even if such combinations or combinations are not explicitly recited in the present invention. In particular, without departing from the spirit and teachings of the present invention, the features recited in the various embodiments and / or claims of the present invention can be combined and / or combined in various ways. All such combinations and / or combinations fall within the scope of the present invention.

[0155] The embodiments of the present invention have been described above. However, these embodiments are for illustrative purposes only and are not intended to limit the scope of the present invention. Although the embodiments have been described separately above, this does not mean that the measures in the respective embodiments cannot be used advantageously in combination. The scope of the present invention is defined by the appended claims and their equivalents. Without departing from the scope of the present invention, those skilled in the art can make various substitutions and modifications, and these substitutions and modifications should all fall within the scope of the present invention.

Claims

1. A method for predicting raw material properties, characterized in that, The method includes: Encoding and decoding a six - tuple to be completed, which consists of raw material type information, raw material name information, raw material unit information, raw material origin information, raw material value attribute information, and timestamp information, to obtain the true complex embedding vectors of the existing attributes in the six - tuple to be completed and the predicted complex embedding vectors for the attributes to be completed in the six - tuple to be completed. The attributes to be completed include any one of the following: the raw material type information, the raw material name information, the raw material unit information, the raw material origin information, the raw material value attribute information. The existing attributes represent the other attributes in the six - tuple to be completed except the attributes to be completed; According to the true complex embedding vectors and the predicted complex embedding vectors, calculate a candidate matching degree evaluation value representing the matching degree between the predicted result of the attribute to be completed and the true information of the existing attributes; According to the candidate matching degree evaluation value, determine the target result predicted for the attribute to be completed.

2. The method according to claim 1, wherein The attribute to be completed is the attribute representing the raw material value attribute information, the predicted result is the raw material value attribute prediction result, the true complex embedding vectors are the raw material type complex embedding vector, the raw material name complex embedding vector, the raw material unit complex embedding vector, the raw material origin complex embedding vector, and the timestamp complex embedding vector; the predicted complex embedding vector is the raw material value attribute complex embedding vector; The calculating a candidate matching degree evaluation value representing the matching degree between the predicted result of the attribute to be completed and the true information of the existing attributes according to the true complex embedding vectors and the predicted complex embedding vectors includes: According to the raw material type complex embedding vector, the raw material name complex embedding vector, the raw material unit complex embedding vector, the raw material origin complex embedding vector, the timestamp complex embedding vector, and the raw material value attribute complex embedding vector, calculate a first matching degree evaluation value between the raw material value attribute prediction result and the raw material type information, the raw material name information, the raw material unit information, the raw material origin information, and the timestamp information; According to the raw material type complex embedding vector, the raw material name complex embedding vector, the raw material unit complex embedding vector, the raw material value attribute complex embedding vector, and the timestamp complex embedding vector, calculate a second matching degree evaluation value between the raw material category information and the raw material unit - value attribute information; Calculate the candidate matching degree evaluation value according to at least one of the first matching degree evaluation value and the second matching degree evaluation value.

3. The method according to claim 2, wherein Calculating a first matching degree evaluation value between the predicted result of the raw material value attribute and the raw material type information, the raw material name information, the raw material unit information, the raw material origin information, and the timestamp information according to the plurality of raw material type embedding vectors, the plurality of raw material name embedding vectors, the plurality of raw material unit embedding vectors, the plurality of raw material origin embedding vectors, the plurality of timestamp embedding vectors, and the plurality of raw material value attribute embedding vectors includes: Using the Hermitian operator, calculating a origin-timestamp interaction complex embedding vector between the plurality of raw material origin embedding vectors and a timestamp unit complex embedding vector obtained by normalizing the plurality of timestamp embedding vectors; Using the Hermitian operator, calculating a category-origin-timestamp interaction complex embedding vector between a raw material category complex embedding vector obtained by splicing the plurality of raw material type embedding vectors and the plurality of raw material name embedding vectors and a origin-timestamp interaction unit complex embedding vector obtained by normalizing the origin-timestamp interaction complex embedding vector; Calculating a first difference between a first argument of the category-origin-timestamp interaction complex embedding vector and a second argument of a raw material unit-value attribute complex embedding vector obtained by splicing the plurality of raw material unit embedding vectors and the plurality of raw material value attribute embedding vectors; Calculating a second difference between a first absolute value of the category-origin-timestamp interaction complex embedding vector and a second absolute value of the raw material unit-value attribute complex embedding vector; Performing an exponential calculation on the first difference and the second difference to obtain the first matching degree evaluation value.

4. The method according to claim 3, wherein Calculating a second matching degree evaluation value between the raw material category information and the raw material unit-value attribute information according to the plurality of raw material type embedding vectors, the plurality of raw material name embedding vectors, the plurality of raw material unit embedding vectors, the plurality of raw material value attribute embedding vectors, and the plurality of timestamp embedding vectors includes: Using the Hermitian operator, calculating a category-timestamp interaction complex embedding vector between the raw material category complex embedding vector and the timestamp unit complex embedding vector; Using the Hermitian operator, calculating a unit-value attribute-timestamp interaction complex embedding vector between the raw material unit-value attribute complex embedding vector and the timestamp unit complex embedding vector; Using the Hermitian operator, calculating a third argument of a calculation result of the Hermitian operator between a preset dependence factor and the category-timestamp interaction complex embedding vector; Performing an exponential calculation on a difference between a third absolute value of the third argument and a fourth absolute value of a fourth argument of the unit-value attribute-timestamp interaction complex embedding vector to obtain the second matching degree evaluation value.

5. The method according to claim 1, characterized in that, Encoding and decoding the to-be-completed six-tuple composed of raw material type information, raw material name information, raw material unit information, raw material origin information, raw material value attribute information, and timestamp information to obtain the true complex embedding vectors of the existing attributes in the to-be-completed six-tuple and the predicted complex embedding vectors for the to-be-completed attributes in the to-be-completed six-tuple includes: Performing one-hot encoding on the existing attributes to obtain an existing attribute binary vector; Performing complex conversion on the existing attribute binary vector to obtain the true complex embedding vector; Performing encoding and decoding on the true complex embedding vector to obtain the predicted complex embedding vector.

6. The method according to claim 1, wherein There are multiple prediction results; Calculating a candidate matching degree evaluation value representing the matching degree between the prediction result of the to-be-completed attribute and the true information of the existing attributes according to the true complex embedding vector and the predicted complex embedding vector includes: Calculating a candidate matching degree evaluation value between each prediction result and the true information according to each predicted complex embedding vector and the true complex embedding vector to obtain multiple candidate matching degree evaluation values; Determining the target result for the prediction of the to-be-completed attribute according to the candidate matching degree evaluation value includes: Determining the prediction result used to calculate the candidate matching degree evaluation value with the largest value among the multiple candidate matching degree evaluation values as the target result.

7. A raw material attribute prediction device, characterized in that, The device includes: A prediction module for encoding and decoding the to-be-completed six-tuple composed of raw material type information, raw material name information, raw material unit information, raw material origin information, raw material value attribute information, and timestamp information to obtain the true complex embedding vectors of the existing attributes in the to-be-completed six-tuple and the predicted complex embedding vectors for the to-be-completed attributes in the to-be-completed six-tuple, where the to-be-completed attributes include any one of the following: the raw material type information, the raw material name information, the raw material unit information, the raw material origin information, the raw material value attribute information, and the existing attributes represent the other attributes in the to-be-completed six-tuple except the to-be-completed attributes; A candidate matching degree evaluation value calculation module for calculating a candidate matching degree evaluation value representing the matching degree between the prediction result of the to-be-completed attribute and the true information of the existing attributes according to the true complex embedding vector and the predicted complex embedding vector; A target result determination module for determining the target result for the prediction of the to-be-completed attribute according to the candidate matching degree evaluation value.

8. An electronic device, including: One or more processors; A memory for storing one or more programs, Characterized in that when the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having executable instructions stored thereon, characterized in that, When the executable instructions are executed by the processor, the processor implements the method according to any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, The computer program implements the method according to any one of claims 1 to 6 when executed by the processor.

Images