Price prediction method and device, electronic equipment and storage medium

Abstract

The invention discloses a price prediction method and device, electronic equipment and a storage medium. The method comprises the following steps: acquiring basic information of a subject matter, wherein the basic information comprises a subject matter name and a target area; a space matrix corresponding to the target area and a fluctuation vector corresponding to the subject matter name are determined, the space matrix comprises a plurality of elements, one element corresponds to one geographic range comprising the target area, the geographic ranges are nested layer by layer, and the fluctuation vector is used for representing the influence degree of objective factors associated with the subject matter on the price; inputting the name of the subject matter and the spatial matrix into a first preset model, and determining a price interval of the subject matter in each geographical range; respectively inputting each price interval and the fluctuation vector into a second preset model, and determining the region price of the subject matter in each geographical range; and calculating the predicted price of the subject matter in the target region according to the prices of all regions. According to the scheme, the price of the subject matter can be quickly and accurately predicted, and reference is provided for scenes such as purchase and transaction.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a price prediction method, device, electronic equipment and storage medium. Background Art

[0002] As a mature transaction method, bidding (hereinafter referred to as bidding) has been widely used in various projects in various industries and fields at home and abroad. The subject matter refers to the goods, services or projects that the bidders are responsible for and provide to the tendering party in the bidding. Therefore, accurately determining the price of the subject matter has great economic significance for both the bidders and the tendering party.

[0003] At present, the price prediction of the underlying asset is mostly based on the historical data of the underlying asset to train the price prediction model, so as to infer the future price changes of the underlying asset based on the price prediction model. However, the existing model training usually requires a large amount of historical data for the accuracy of the prediction, occupies a large amount of hardware computing resources, and the entire prediction process takes a long time. Summary of the invention

[0004] The present invention provides a price prediction method, device, electronic device and storage medium, which can quickly and accurately predict the price of a subject matter and provide a reference for scenarios such as procurement and trading.

[0005] According to one aspect of the present invention, there is provided a price prediction method, comprising:

[0006] Obtaining basic information of the subject matter, wherein the basic information includes the name of the subject matter and the target area;

[0007] Determine the spatial matrix corresponding to the target area and the volatility vector corresponding to the name of the underlying asset, wherein the spatial matrix includes multiple elements, one element corresponds to a geographical range including the target area, and the geographical ranges are nested layer by layer. The volatility vector is used to characterize the degree of influence of objective factors associated with the underlying asset on the price;

[0008] Input the name of the subject matter and the spatial matrix into the first preset model to determine the price range of the subject matter in each geographical range;

[0009] Input each price range and volatility vector into a second preset model to determine the regional price of the underlying asset in each geographic range;

[0010] Based on all regional prices, calculate the predicted price of the underlying asset in the target area.

[0011] Optionally, the first element in the spatial matrix corresponds to a geographic range size equal to the size of the target area;

[0012] The geographical range sizes corresponding to the elements in the spatial matrix are in an arithmetically increasing sequence, either increasing exponentially or exponentially.

[0013] Optionally, determining the volatility vector corresponding to the name of the underlying asset includes:

[0014] Determine objective factors associated with the subject matter according to the name of the subject matter, wherein the objective factors include at least one of the type of the subject matter, production information of the subject matter, raw material information of the subject matter, transaction information of the subject matter, and transaction form of the subject matter;

[0015] The volatility factor of each objective factor is obtained separately, and a volatility vector is constructed based on all volatility factors.

[0016] Optionally, the first preset model is a decision tree model, the second preset model is a neural network model or a deep learning model, and the input end of the second preset model is provided with a function library;

[0017] For any price range, the price range and the fluctuation vector are input into the second preset model to determine the regional price of the underlying asset in the geographical range, including:

[0018] Constructing a model prompt word according to the price range and at least one function in the function library;

[0019] The model prompt words and the volatility vector are input into a second preset model to determine the regional price of the underlying asset within a geographical range.

[0020] Optionally, calculate the predicted price of the underlying asset in the target region based on prices in all regions, including:

[0021] Determine the regional weights for each geographic area;

[0022] Calculate the benchmark price of the underlying asset in the target area based on all regional prices and their corresponding regional weights;

[0023] The predicted price of the underlying asset in the target area is calculated based on the benchmark price and the correction coefficient, where the correction coefficient is used to characterize the degree of influence of time on the price of the underlying asset.

[0024] Optionally, determine the regional weights for each geographic area, including:

[0025] According to the name of the underlying object, obtain the transaction information of the underlying object in each geographical range;

[0026] Based on natural language processing (NLP) technology, we extract transaction keywords from each transaction information and determine the economic activity of the subject matter in each geographical range based on the transaction keywords.

[0027] The regional weight of each geographical scope is determined based on the economic activity, where the sum of all regional weights is 1, and the regional weight of a geographical scope is positively correlated with the economic activity of the geographical scope.

[0028] Optionally, the benchmark price of the underlying asset in the target area is calculated based on all regional prices and their corresponding regional weights, including:

[0029] Selecting a geographical range whose regional weight is greater than or equal to a first preset threshold as a target range, and fine-tuning the regional weight of the target range, wherein the sum of the regional weights of all target ranges after fine-tuning is 1;

[0030] The benchmark price of the underlying asset in the target area is calculated based on the regional prices of the underlying asset in the target range and its corresponding fine-tuned regional weights.

[0031] Optionally, after selecting a geographical range whose regional weight is greater than or equal to a first preset threshold as the target range, the method further includes:

[0032] Determine whether the sum of the regional weights corresponding to the target range is greater than or equal to a second preset threshold;

[0033] If the sum of the regional weights corresponding to the target range is greater than or equal to the second preset threshold, then continue to perform the step of fine-tuning the regional weights of the target range;

[0034] If the sum of the regional weights corresponding to the target range is less than the second preset threshold, the process returns to the step of determining the spatial matrix corresponding to the target area until the sum of the regional weights corresponding to the target range is greater than or equal to the second preset threshold.

[0035] According to another aspect of the present invention, there is provided a price prediction device, comprising: an acquisition module, a determination module, a prediction module and a calculation module;

[0036] An acquisition module, used to acquire basic information of the subject matter, wherein the basic information includes the name of the subject matter and the target area;

[0037] A determination module, used to determine a spatial matrix corresponding to the target area and a fluctuation vector corresponding to the name of the underlying object, wherein the spatial matrix includes a plurality of elements, one element corresponds to a geographical range including the target area, and the geographical ranges are nested layer by layer, and the fluctuation vector is used to characterize the degree of influence of objective factors associated with the underlying object on the price;

[0038] A prediction module, for inputting the name of the underlying object and the spatial matrix into a first preset model to determine the price range of the underlying object in each geographical range; and for inputting each price range and fluctuation vector into a second preset model to determine the regional price of the underlying object in each geographical range;

[0039] The calculation module is used to calculate the predicted price of the underlying asset in the target area based on the prices in all regions.

[0040] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0041] at least one processor; and a memory in communication with the at least one processor; wherein,

[0042] The memory stores a computer program that can be executed by at least one processor. The computer program is executed by at least one processor so that the at least one processor can execute the price prediction method of any embodiment of the present invention.

[0043] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to implement the price prediction method of any embodiment of the present invention when executed by a processor.

[0044] The technical solution of the embodiment of the present invention is to determine the spatial matrix corresponding to the target area, input the name of the subject matter and the spatial matrix into the first preset model, obtain the price range of the subject matter in each geographical range, and then input the fluctuation vectors corresponding to each price range and the name of the subject matter into the second preset model respectively, determine the regional price of the subject matter in each geographical range, and thus calculate the predicted price of the subject matter in the target area according to all regional prices. In the price prediction method provided by the present invention, on the one hand, since the basic information of the subject matter includes the target area, the subject matter and the geographical location are associated, thereby avoiding the influence of the different prices of the same subject matter in different regions on the prediction results. On the other hand, the price range of the subject matter in each geographical range is first determined by the first preset model, and then the regional price of the subject matter in each geographical range is determined by the second preset model, so as to realize the prediction of the price from coarse to fine, and the use of two preset models can reduce the data processing scale of each model, improve the processing speed of the model, and reduce the demand for hardware. In addition, since the fluctuation vector reflects the degree of influence of the objective factors associated with the subject matter on the price, the prediction accuracy of the regional price can be further guaranteed. Thirdly, the predicted price of the subject matter in the target area is calculated based on the prices of all regions, taking into account the impact of different geographical ranges on the predicted price, making the prediction result more accurate, thus providing a reference for procurement, trading and other scenarios.

[0045] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0047] Figure 1 It is a flowchart of a price prediction method provided by Embodiment 1 of the present invention;

[0048] Figure 2 It is a flowchart of a price prediction method provided by Embodiment 2 of the present invention;

[0049] Figure 3 is a schematic diagram of the structure of a price prediction device provided by Embodiment 3 of the present invention;

[0050] Figure 4 It is a structural schematic diagram of an electronic device provided in Embodiment 4 of the present invention. DETAILED DESCRIPTION

[0051] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0052] It should be noted that the terms "first", "second", "target", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0053] Embodiment 1

[0054] Figure 11 is a flowchart of a price prediction method provided in the first embodiment of the present invention. This embodiment can be applied to the price prediction of the subject matter involved in bidding. The method can be executed by a price prediction device, which can be implemented in the form of hardware and / or software, and can be configured in an electronic device (such as a computer device such as a server). Figure 1 As shown, the method includes:

[0055] S110: Obtain basic information of the target object, wherein the basic information includes the name of the target object and the target area.

[0056] In the present invention, the subject matter is all the price-related items, services or projects involved in the bidding, for example: food, oil, machine tools and other items, translation, technical support and other services, water conservancy, roads, construction and other projects.

[0057] The basic information of the subject matter includes the name of the subject matter and the target area. Through the basic information of the subject matter, the price prediction device can know that the prediction task is to predict the price of the subject matter in the target area. Since the price of the same subject matter may be different in different regions (such as the price of vegetable A in region A is different from the price in region B), the concept of target area is introduced in the basic information of the subject matter, so as to realize the association between the subject matter and the geographical location, so as to make targeted predictions.

[0058] In an optional implementation, the price prediction device may receive a prediction request, and obtain the basic information of the subject matter carried in the prediction request by parsing the prediction request. In another optional implementation, the price prediction device may include an input device (such as a touch display / keyboard), and the basic information of the subject matter input by the user may be directly received through the input device.

[0059] S120. Determine a spatial matrix corresponding to the target area and a volatility vector corresponding to the name of the underlying object, wherein the spatial matrix includes a plurality of elements, one element corresponds to a geographical range including the target area, and the geographical ranges are nested layer by layer. The volatility vector is used to characterize the degree of influence of objective factors associated with the underlying object on the price.

[0060] In step S120, there is no order of execution between "determining the spatial matrix corresponding to the target area" and "determining the wave vector corresponding to the target object name". "Determining the spatial matrix corresponding to the target area" may be executed first, and then "determining the wave vector corresponding to the target object name"; "determining the wave vector corresponding to the target object name" may be executed first, and then "determining the spatial matrix corresponding to the target area"; "determining the spatial matrix corresponding to the target area" and "determining the wave vector corresponding to the target object name" may also be executed at the same time.

[0061] The space matrix may include multiple elements. For example, the space matrix may be represented as There are mn elements in total, each of which corresponds to a geographical range that includes the target area, and the geographical ranges are nested. Usually, the size of the geographical range corresponding to the first element in the spatial matrix is ​​equal to the size of the target area, that is, element a 11 is the target area.

[0062] In the present invention, the spatial matrix can be determined according to a preset rule. For example, the spatial matrix includes 5 elements, which are the target area, the street where the target area is located, the administrative district where the target area is located, the city where the target area is located, and the province where the target area is located. For another example, the spatial matrix includes 4 elements, which are the target area, the area within 1 km of the target area, the area within 5 km of the target area, and the area within 10 km of the target area.

[0063] The volatility vector can be constructed based on the volatility factors corresponding to the objective factors associated with the underlying asset. Specifically, objective factors refer to external conditions or circumstances that may affect the value, performance, or status of the underlying asset.

[0064] S130: Input the name of the subject matter and the spatial matrix into the first preset model to determine the price range of the subject matter in each geographical range.

[0065] The first preset model is a pre-trained decision tree model. The decision tree model is a model that infers target values ​​from data features by learning simple decision rules. In order to prevent the decision tree model from overfitting, the present invention can be controlled by pruning (including pre-pruning (before generation) and post-pruning (after generation)), setting the maximum depth, etc.

[0066] By inputting the name of the subject matter and the spatial matrix into the first preset model, the price range of the subject matter in each geographical scope can be determined, thereby achieving a rough determination of the price of the subject matter in each geographical scope, providing a data basis for the subsequent precise determination of the price.

[0067] S140. Input each price range and fluctuation vector into the second preset model respectively to determine the regional price of the subject matter in each geographical range.

[0068] The second preset model is a pre-trained neural network model or a deep learning model, wherein the deep learning model can be a long short-term memory network (Long Short-Term Memory, LSTM) prediction model, etc.; the neural network model can be a convolutional neural network (Convolutional Neural Networks, CNN) model, a deep convolutional neural network (Deep Convolutional Neural Networks, DCNN) model, etc.

[0069] For any price range, the price range and fluctuation vector are input into the second preset model to determine the regional price of the underlying asset in each geographical range. In this way, the price forecast from coarse to fine is achieved, and the use of two preset models can reduce the data processing scale of each model, improve the processing speed of the model, and reduce the demand for hardware.

[0070] In addition, since the volatility vector reflects the degree of influence of objective factors associated with the underlying asset on the price, the accuracy of regional price prediction can be further guaranteed.

[0071] S150. Calculate the predicted price of the subject matter in the target area based on prices in all regions.

[0072] After all regional prices are determined, all regional prices can be weighted, averaged, maximized, minimized, etc. to calculate the predicted price of the subject matter in the target area. In this way, the impact of different geographical ranges on the predicted price can be comprehensively considered, making the prediction result more accurate, thus providing a reference for procurement, trading and other scenarios.

[0073] In one embodiment, the price prediction device may display the predicted price to the user, or push the predicted price to the user's terminal device, for example, directly displaying that the predicted price of a certain target object in the target area is 500 yuan / kg.

[0074] Embodiment 2

[0075] Figure 2 FIG. 1 is a flow chart of a price prediction method provided by Embodiment 2 of the present invention. Based on the above Embodiment 1, this embodiment provides a specific implementation method of price prediction. Figure 2 As shown, the method includes:

[0076] S201. Obtain basic information of the target object, wherein the basic information includes the name of the target object and the target area.

[0077] In the present invention, the subject matter is all the price-related items, services or projects involved in the bidding, for example: food, oil, machine tools and other items, translation, technical support and other services, water conservancy, roads, construction and other projects.

[0078] The basic information of the subject matter includes the name of the subject matter and the target area. Since the price of the same subject matter may be different in different regions (for example, the price of vegetable A in region A is different from that in region B), introducing the concept of target area into the basic information of the subject matter can realize the association between the subject matter and the geographical location, so as to make targeted predictions.

[0079] In an optional implementation, the price prediction device may receive a prediction request, and obtain the basic information of the subject matter carried in the prediction request by parsing the prediction request. In another optional implementation, the price prediction device may include an input device (such as a touch display / keyboard), and the basic information of the subject matter input by the user may be directly received through the input device.

[0080] S202: Determine a spatial matrix corresponding to the target area.

[0081] Among them, the space matrix includes multiple elements. For example, the space matrix can be expressed as There are mn elements in total, one element corresponds to a geographical range including the target area, and the geographical ranges are nested. In one embodiment, the spatial matrix can be any of the following: a spatial adjacency matrix, a geographical distance matrix, an economic distance matrix, and an economic and geographical nested matrix.

[0082] Usually, the first element in the spatial matrix corresponds to a geographic range that is equal to the size of the target area. The element a in 11 is the target area.

[0083] The spatial matrix can be determined according to preset rules. For example, the spatial matrix can be determined according to urban agglomerations or administrative regions, or according to the distance from the target area or the size of the geographical range. When the spatial matrix is ​​determined according to the size of the geographical range, the size of the geographical range corresponding to the elements in the spatial matrix is ​​an arithmetic increasing series, or increases in multiples, or increases exponentially.

[0084] Example 1: When the spatial matrix is ​​determined according to urban agglomerations, the spatial matrix may include four elements, namely, the target area, the metropolitan area where the target area is located, the sub-regional urban agglomeration where the target area is located, and the super urban agglomeration where the target area is located.

[0085] Example 2: When the spatial matrix is ​​determined according to administrative regions, the spatial matrix may include five elements, namely, the target region, the street where the target region is located, the administrative region where the target region is located, the city where the target region is located, and the province where the target region is located.

[0086] Example 3: When the spatial matrix is ​​determined according to the distance from the target area, the spatial matrix may include 4 elements, namely the target area, the area within 1 km of the target area, the area within 5 km of the target area, and the area within 10 km of the target area.

[0087] Example 4: When the spatial matrix is ​​determined according to the size of the geographical range, the spatial matrix may include 4 elements, namely, the target area, an area twice as large as the target area, an area four times as large as the target area, and an area eight times as large as the target area.

[0088] S203. Determine objective factors associated with the subject matter according to the name of the subject matter, wherein the objective factors include at least one of the subject matter type, subject matter production information, subject matter raw material information, subject matter transaction information, and subject matter transaction form.

[0089] Different subject matters may have different associated objective factors. For example, if the subject matter is vegetables, the associated objective factors are mainly the origin, climate, and transportation conditions; if the subject matter is building materials, the associated objective factors are mainly raw material information (such as raw material origin, price, etc.) and production difficulty. Therefore, the present invention first needs to determine the objective factors associated with the subject matter for the name of the subject matter.

[0090] S204. Obtain the volatility factor of each objective factor respectively, and construct a volatility vector based on all volatility factors.

[0091] Specifically, the volatility factor of each objective factor can be obtained by looking up a table or dynamically calculated through historical economic information.

[0092] For example, the fluctuation vector can be expressed as (b1, b2, ..., b x ), where x represents the number of objective factors associated with the subject matter, and b i Represents the volatility factor of the i-th objective factor associated with the underlying asset.

[0093] S205: Input the name of the subject matter and the spatial matrix into the first preset model to determine the price range of the subject matter in each geographical range.

[0094] The first preset model is a pre-trained decision tree model. The decision tree model is a model that infers target values ​​from data features by learning simple decision rules. In order to prevent the decision tree model from overfitting, the present invention can be controlled by pruning (including pre-pruning (before generation) and post-pruning (after generation)), setting the maximum depth, etc.

[0095] By inputting the name of the subject matter and the spatial matrix into the first preset model, the price range of the subject matter in each geographical scope can be determined, thereby achieving a rough determination of the price of the subject matter in each geographical scope, providing a data basis for the subsequent precise determination of the price.

[0096] S206: For any price range, construct a model prompt word according to the price range and at least one function in the function library.

[0097] S207: Input the model prompt word and the volatility vector into a second preset model to determine the regional price of the underlying asset within the geographical scope.

[0098] In combination with steps S206 and S207, it can be seen that since there are multiple price ranges, steps S206-S207 need to be executed for each price range to determine the regional price of the subject matter within the geographical scope.

[0099] The second preset model is a pre-trained neural network model or a deep learning model, wherein the deep learning model may be an LSTM prediction model, etc.; the neural network model may be a CNN model, a DCNN model, etc. The input end of the second preset model is provided with a function library.

[0100] The function library usually includes several functions. A model prompt word is constructed according to the price range and at least one function in the function library. In this way, the model prompt word can be used as the input of the second preset model to optimize the input of the model and ensure that the second preset model can work according to the established mode, thereby ensuring the accuracy of the regional prices determined subsequently.

[0101] S208. Determine the regional weight of each geographical range.

[0102] In one embodiment, “determining the regional weight of each geographical range” may include the following three steps.

[0103] Step A1: According to the name of the subject matter, obtain the transaction information of the subject matter in each geographical range.

[0104] Transaction information may include transaction amount, transaction time and other transaction-related information.

[0105] Optionally, after obtaining the transaction information of the subject matter in each geographical range, the transaction information can also be pre-processed, such as deduplication, filling in missing values, and removing obviously erroneous values.

[0106] Step A2: Based on Natural Language Processing (NLP) technology, extract transaction keywords from each transaction information, and determine the economic activity of the subject matter in each geographical range based on the transaction keywords.

[0107] NLP technology is a branch of computer science and artificial intelligence, which is dedicated to enabling computers to understand, interpret and generate content in human language. It is widely used in machine translation, public opinion monitoring, automatic summarization, opinion extraction, text classification, question answering, text semantic comparison, speech recognition and other scenarios.

[0108] In the present invention, the price prediction device can extract transaction keywords from each transaction information based on NLP technology. Different transaction keywords correspond to different economic activities, so as to determine the economic activity of the subject matter in each geographical range according to the transaction keywords.

[0109] Step A3: Determine the regional weight of each geographical area based on the economic activity, where the sum of all regional weights is 1, and the regional weight of a geographical area is positively correlated with the economic activity of the geographical area.

[0110] For example, assume that there are 3 elements in the spatial matrix, element 1 corresponds to geographic scope 1 (i.e., the target area itself), element 2 corresponds to geographic scope 2, and element 3 corresponds to geographic scope 3. The economic activity of geographic scope 1 is 50, the economic activity of geographic scope 2 is 100, and the economic activity of geographic scope 3 is 50, so the final regional weight of geographic scope 1 is 0.25, the regional weight of geographic scope 2 is 0.5, and the regional weight of geographic scope 3 is 0.25.

[0111] S209. Calculate the benchmark price of the subject matter in the target area based on all regional prices and their corresponding regional weights.

[0112] In a first possible implementation, the price prediction device may directly calculate the base price of the subject matter in the target area based on all regional prices and their corresponding regional weights.

[0113] In a second possible implementation, the price prediction device may select a geographical range whose regional weight is greater than or equal to a first preset threshold as the target range, and fine-tune the regional weight of the target range, wherein the sum of the regional weights of all target ranges after fine-tuning is 1; and then calculate the benchmark price of the subject matter in the target area based on the regional price of the subject matter in the target range and its corresponding fine-tuned regional weight.

[0114] For example, assume that there are 3 elements in the spatial matrix, element 1 corresponds to geographic scope 1 (i.e. the target area itself), element 2 corresponds to geographic scope 2, and element 3 corresponds to geographic scope 3. The regional weight of geographic scope 1 is 0.45, the regional weight of geographic scope 2 is 0.5, and the regional weight of geographic scope 3 is 0.05. The value of the first preset threshold is 0.1. It can be seen that the regional weight of geographic scope 3 is less than the first preset threshold, indicating that the correlation between geographic scope 3 and the price of the subject matter is relatively low, and geographic scope 3 is no longer involved in the subsequent benchmark price determination process. In this way, the prediction accuracy of the benchmark price can be improved while reducing the difficulty of calculation.

[0115] Optionally, for the second possible implementation method, after selecting a geographical range whose regional weight is greater than or equal to a first preset threshold as the target range, it is also possible to determine whether the sum of the regional weights corresponding to the target range is greater than or equal to a second preset threshold; if the sum of the regional weights corresponding to the target range is greater than or equal to the second preset threshold, it indicates that the spatial matrix determined in step S202 is relatively reasonable, and at this time, continue to perform the step of fine-tuning the regional weights of the target range; if the sum of the regional weights corresponding to the target range is less than the second preset threshold, it indicates that the spatial matrix determined in step S202 is unreasonable, and it is necessary to return to execute step 202 until the sum of the regional weights corresponding to the target range is greater than or equal to the second preset threshold.

[0116] In this way, the rationality of the spatial matrix layout is further verified, ensuring a strong correlation between the target object and the spatial matrix.

[0117] S210. Calculate the predicted price of the subject matter in the target area based on the base price and the correction coefficient, wherein the correction coefficient is used to characterize the degree of influence of time on the price of the subject matter.

[0118] In one embodiment, the predicted price of the subject matter in the target area is equal to the product of the base price and the correction coefficient.

[0119] The correction factor is used to characterize the degree of influence of time on the price of the underlying asset. The lower the influence of time on the price of the underlying asset, the closer the value of the correction factor is to 1. If time has no influence on the price of the underlying asset, the value of the correction factor is 1.

[0120] Optionally, the correction coefficient is between 0.5 and 1.5. Preferably, the correction coefficient is between 0.8 and 1.2.

[0121] In one embodiment, the price prediction device may display the predicted price to the user, or push the predicted price to the user's terminal device, for example, directly displaying that the predicted price of a certain target object in the target area is 500 yuan / kg.

[0122] The technical solution of the embodiment of the present invention is to determine the spatial matrix corresponding to the target area, input the name of the subject matter and the spatial matrix into the first preset model, obtain the price range of the subject matter in each geographical range, and then input the fluctuation vectors corresponding to each price range and the name of the subject matter into the second preset model respectively, determine the regional price of the subject matter in each geographical range, and thus calculate the predicted price of the subject matter in the target area according to all regional prices. In the price prediction method provided by the present invention, on the one hand, since the basic information of the subject matter includes the target area, the subject matter and the geographical location are associated, thereby avoiding the influence of the different prices of the same subject matter in different regions on the prediction results. On the other hand, the price range of the subject matter in each geographical range is first determined by the first preset model, and then the regional price of the subject matter in each geographical range is determined by the second preset model, so as to realize the prediction of the price from coarse to fine, and the use of two preset models can reduce the data processing scale of each model, improve the processing speed of the model, and reduce the demand for hardware. In addition, since the fluctuation vector reflects the degree of influence of the objective factors associated with the subject matter on the price, the prediction accuracy of the regional price can be further guaranteed. Thirdly, the predicted price of the subject matter in the target area is calculated based on the prices of all regions, taking into account the impact of different geographical ranges on the predicted price, making the prediction result more accurate, thus providing a reference for procurement, trading and other scenarios.

[0123] Embodiment 3

[0124] Figure 3 Schematic diagram of the structure of a price prediction device provided by Embodiment 3 of the present invention. Figure 3 As shown, the device includes: an acquisition module 301, a determination module 302, a prediction module 303 and a calculation module 304.

[0125] The acquisition module 301 is used to acquire basic information of the target object, wherein the basic information includes the name of the target object and the target area;

[0126] A determination module 302 is used to determine a spatial matrix corresponding to the target area and a fluctuation vector corresponding to the name of the underlying object, wherein the spatial matrix includes a plurality of elements, one element corresponds to a geographical range including the target area, and the geographical ranges are nested layer by layer, and the fluctuation vector is used to characterize the degree of influence of objective factors associated with the underlying object on the price;

[0127] Prediction module 303, for inputting the name of the subject matter and the spatial matrix into the first preset model to determine the price range of the subject matter in each geographical range; respectively inputting each price range and the fluctuation vector into the second preset model to determine the regional price of the subject matter in each geographical range;

[0128] The calculation module 304 is used to calculate the predicted price of the subject matter in the target area based on the prices in all regions.

[0129] Optionally, the first element in the spatial matrix corresponds to a geographic range size equal to the size of the target area;

[0130] The geographical range sizes corresponding to the elements in the spatial matrix are in an arithmetically increasing sequence, either increasing exponentially or exponentially.

[0131] Optionally, the determination module 302 is specifically used to determine the objective factors associated with the subject matter based on the name of the subject matter, wherein the objective factors include at least one of the subject matter type, subject matter production information, subject matter raw material information, subject matter transaction information, and subject matter transaction form; respectively obtain the volatility factor of each objective factor, and construct a volatility vector based on all volatility factors.

[0132] Optionally, the first preset model is a decision tree model, the second preset model is a neural network model or a deep learning model, and the input end of the second preset model is provided with a function library;

[0133] The prediction module 303 is specifically used to construct a model prompt word according to the price range and at least one function in the function library; input the model prompt word and the fluctuation vector into the second preset model to determine the regional price of the subject matter in the geographical range.

[0134] Optionally, the calculation module 304 is specifically used to determine the regional weight of each geographical range; calculate the benchmark price of the subject matter in the target area based on all regional prices and their corresponding regional weights; calculate the predicted price of the subject matter in the target area based on the benchmark price and the correction coefficient, wherein the correction coefficient is used to characterize the degree of influence of time on the price of the subject matter.

[0135] Optionally, the calculation module 304 is specifically used to obtain transaction information of the subject matter in each geographical scope according to the name of the subject matter; based on natural language processing (NLP) technology, extract transaction keywords from each transaction information respectively, and determine the economic activity of the subject matter in each geographical scope according to the transaction keywords; determine the regional weight of each geographical scope according to the economic activity, wherein the sum of all regional weights is 1, and the regional weight of a geographical scope is positively correlated with the economic activity of the geographical scope.

[0136] Optionally, the calculation module 304 is specifically used to select a geographical range whose regional weight is greater than or equal to a first preset threshold as the target range, and fine-tune the regional weight of the target range, wherein the sum of the regional weights of all target ranges after fine-tuning is 1; and calculate the benchmark price of the subject matter in the target area based on the regional price of the subject matter in the target range and its corresponding fine-tuned regional weight.

[0137] Optionally, the calculation module 304 is also used to determine whether the sum of the regional weights corresponding to the target range is greater than or equal to a second preset threshold after selecting a geographical range whose regional weight is greater than or equal to a first preset threshold as the target range; if the sum of the regional weights corresponding to the target range is greater than or equal to the second preset threshold, continue to execute the step of fine-tuning the regional weights of the target range; if the sum of the regional weights corresponding to the target range is less than the second preset threshold, the determination module 302 returns to execute the step of determining the spatial matrix corresponding to the target area until the sum of the regional weights corresponding to the target range is greater than or equal to the second preset threshold.

[0138] The price prediction device provided in the embodiment of the present invention can execute the price prediction method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0139] Embodiment 4

[0140] Figure 4 A schematic diagram of the structure of an electronic device 10 that can be used to implement an embodiment 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 processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0141] like Figure 4As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0142] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0143] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 performs the various methods and processes described above, such as a price prediction method.

[0144] In some embodiments, the price prediction method may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the price prediction method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to perform the price prediction method in any other suitable manner (e.g., by means of firmware).

[0145] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0146] Computer programs for implementing 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, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0147] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0148] To provide interaction with a user, the systems and techniques described herein may 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 a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0149] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0150] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0151] An embodiment of the present invention further provides a computer program product, including a computer program, which, when executed by a processor, implements the behavior operation determination method provided by any embodiment of the present invention.

[0152] In the process of implementation, the computer program product can be written in one or more programming languages ​​or a combination thereof to perform the computer program code of the present invention, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (for example, using an Internet service provider to connect through the Internet).

[0153] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0154] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A price prediction method, characterized in that: include: Acquire basic information of the subject matter, wherein the basic information includes the name of the subject matter and the target area; Determine a spatial matrix corresponding to the target area and a fluctuation vector corresponding to the name of the underlying object, wherein the spatial matrix includes a plurality of elements, one of the elements corresponds to a geographical range including the target area, the geographical ranges are nested layer by layer, and the fluctuation vector is used to characterize the degree of influence of objective factors associated with the underlying object on the price; Inputting the name of the subject matter and the spatial matrix into a first preset model to determine a price range of the subject matter in each of the geographical ranges; Inputting each of the price ranges and the fluctuation vectors into a second preset model respectively to determine the regional price of the subject matter in each of the geographical ranges; Based on all the regional prices, the predicted price of the subject matter in the target area is calculated.

2. The price prediction method according to claim 1, characterized in that: The size of the geographical range corresponding to the first element in the spatial matrix is ​​equal to the size of the target area; The sizes of geographical ranges corresponding to the elements in the spatial matrix are in an arithmetically increasing sequence, or increase in multiples, or increase in exponentials.

3. The price prediction method according to claim 1, characterized in that: The determining the fluctuation vector corresponding to the name of the target object includes: According to the name of the subject matter, determine the objective factors associated with the subject matter, wherein the objective factors include at least one of the type of the subject matter, the production information of the subject matter, the raw material information of the subject matter, the transaction information of the subject matter, and the transaction form of the subject matter; The fluctuation factor of each objective factor is obtained respectively, and the fluctuation vector is constructed according to all the fluctuation factors.

4. The price prediction method according to claim 1, characterized in that: The first preset model is a decision tree model, the second preset model is a neural network model or a deep learning model, and the input end of the second preset model is provided with a function library; For any price range, inputting the price range and the fluctuation vector into a second preset model to determine the regional price of the subject matter in the geographical range includes: constructing a model prompt word according to the price range and at least one function in the function library; The model prompt word and the fluctuation vector are input into the second preset model to determine the regional price of the subject matter in the geographical range.

5. The price prediction method according to claim 1, characterized in that: The step of calculating the predicted price of the subject matter in the target area based on all the regional prices includes: determining a regional weight for each of said geographic areas; Calculate the benchmark price of the subject matter in the target area based on all the regional prices and their corresponding regional weights; The predicted price of the subject matter in the target area is calculated based on the base price and the correction coefficient, wherein the correction coefficient is used to characterize the degree of influence of time on the price of the subject matter.

6. The price prediction method according to claim 5, characterized in that: Determining the regional weight of each of the geographical areas comprises: According to the name of the subject matter, obtaining transaction information of the subject matter in each of the geographical ranges; Based on natural language processing (NLP) technology, extract transaction keywords from each of the transaction information, and determine the economic activity of the subject matter in each of the geographical areas according to the transaction keywords; The regional weight of each of the geographical areas is determined according to the economic activity, wherein the sum of all regional weights is 1, and the regional weight of the geographical area is positively correlated with the economic activity of the geographical area.

7. The price prediction method according to claim 5, characterized in that: The step of calculating the base price of the subject matter in the target area according to all the regional prices and their corresponding regional weights includes: Selecting a geographical range whose regional weight is greater than or equal to a first preset threshold as a target range, and fine-tuning the regional weight of the target range, wherein the sum of the regional weights of all the target ranges after fine-tuning is 1; The base price of the subject matter in the target area is calculated based on the regional price of the subject matter in the target range and its corresponding fine-tuned regional weight.

8. The price prediction method according to claim 7, characterized in that: After selecting a geographical range whose regional weight is greater than or equal to a first preset threshold as a target range, the method further includes: Determining whether the sum of the regional weights corresponding to the target range is greater than or equal to a second preset threshold; If the sum of the regional weights corresponding to the target range is greater than or equal to the second preset threshold, then continue to perform the step of fine-tuning the regional weights of the target range; If the sum of the regional weights corresponding to the target range is less than the second preset threshold, the process returns to the step of determining the spatial matrix corresponding to the target area until the sum of the regional weights corresponding to the target range is greater than or equal to the second preset threshold.

9. A price prediction device, characterized in that: include: Acquisition module, determination module, prediction module and calculation module; The acquisition module is used to acquire basic information of the target object, wherein the basic information includes the name of the target object and the target area; The determination module is used to determine a spatial matrix corresponding to the target area and a fluctuation vector corresponding to the name of the underlying object, wherein the spatial matrix includes a plurality of elements, one of the elements corresponds to a geographical range including the target area, and the geographical ranges are nested layer by layer, and the fluctuation vector is used to characterize the degree of influence of objective factors associated with the underlying object on the price; The prediction module is used to input the name of the subject matter and the spatial matrix into a first preset model to determine the price range of the subject matter in each of the geographical ranges; and input each of the price ranges and the fluctuation vector into a second preset model to determine the regional price of the subject matter in each of the geographical ranges; The calculation module is used to calculate the predicted price of the subject matter in the target area based on all the regional prices.

10. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory in communication with the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can perform the price prediction method according to any one of claims 1 to 8.

11. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the price prediction method according to any one of claims 1 to 8 when executed.

Images