Information processing method, device and storage medium

Abstract

The embodiments of the present application disclose an information processing method and device, and a storage medium, including: obtaining first historical operation data associated with an object at an object demand side, and obtaining second historical operation data associated with the object at an object supply side; obtaining object attributes at the object supply side and demand attributes at the object demand side; inputting the first historical operation data, the second historical operation data, the object attributes, and the demand attributes into a supply-demand correlation model to obtain the correlation between the object supply side and the object demand side, so as to search for a target demand corresponding to the object supply side in the object demand side based on the correlation, or to search for a target object supply side related to the object demand side in the object supply side; the supply-demand correlation model is a model obtained by learning historical browsing operation data through unsupervised learning.

Description

Technical Field

[0001] The present application relates to the field of information processing technology, and in particular to an information processing method and device, and a storage medium. Background Art

[0002] With the continuous development of Internet technology, it usually helps to match trades between product suppliers and retailers in various places, determine the supply and demand relationship between suppliers and retailers, and maximize the supply and demand value between suppliers and brand owners.

[0003] In the prior art, in the process of matching the supply and demand pattern formed by multi-layer nested resources and multi-layer demand structures, the supply and demand relationship between goods and demands is obtained by decomposing resources and demands into multiple levels to determine whether the attribute points in each level match. Since there are differences in importance between different attributes of different goods, the accuracy of the supply and demand relationship directly determined based on the attribute points in each level is low. Summary of the invention

[0004] In order to solve the above technical problems, the embodiments of the present application hope to provide an information processing method and device, and a storage medium, which can improve the accuracy of the determined supply and demand relationship.

[0005] The technical solution of this application is implemented as follows:

[0006] The present invention provides an information processing method, which includes:

[0007] Acquire first historical operation data associated with the object at the object demand side, and acquire second historical operation data associated with the object at the object supply side; acquire object attributes at the object supply side and demand attributes at the object demand side;

[0008] The first historical operation data, the second historical operation data, the object attributes and the demand attributes are input into a supply and demand correlation model to obtain the correlation between the object supply side and the object demand side, so as to find the target demand corresponding to the object supply side in the object demand side based on the correlation, or to find the target object supply side related to the object demand side in the object supply side; the supply and demand correlation model is a model obtained by learning historical browsing operation data through unsupervised learning.

[0009] The present application provides an information processing device, the device comprising:

[0010] An acquisition unit, configured to acquire first historical operation data associated with an object at an object demand side, and acquire second historical operation data associated with the object at an object supply side; and acquire object attributes at the object supply side and demand attributes at the object demand side;

[0011] An input unit is used to input the first historical operation data, the second historical operation data, the object attributes and the demand attributes into a supply and demand correlation model to obtain the correlation between the object supply side and the object demand side, so as to search the target demand corresponding to the object supply side in the object demand side based on the correlation, or to search the target object supply side related to the object demand side in the object supply side; the supply and demand correlation model is a model obtained by learning historical browsing operation data through unsupervised learning.

[0012] The present application provides an information processing device, the device comprising:

[0013] A memory, a processor and a communication bus, wherein the memory communicates with the processor via the communication bus, and the memory stores an information processing program executable by the processor. When the information processing program is executed, the information processing method described above is executed by the processor.

[0014] An embodiment of the present application provides a storage medium having a computer program stored thereon, which is applied to an information processing device, and is characterized in that the computer program implements the above-mentioned information processing method when executed by a processor.

[0015] The embodiments of the present application provide an information processing method, an apparatus, and a storage medium. The information processing method includes: obtaining first historical operation data associated with an object at an object demand side and obtaining second historical operation data associated with the object at an object supply side; obtaining object attributes at the object supply side and demand attributes at the object demand side; inputting the first historical operation data, the second historical operation data, the object attributes, and the demand attributes into a supply and demand correlation model to obtain the correlation between the object supply side and the object demand side, so as to search for a target demand corresponding to the object supply side in the object demand side based on the correlation, or to search for a target object supply side related to the object demand side in the object supply side; the supply and demand correlation model is a model obtained by learning historical browsing operation data through unsupervised learning. By adopting the above method to implement the scheme, the information processing device inputs the first historical operation data, the second historical operation data, the object attributes and the demand attributes into the supply and demand correlation model, and uses unsupervised learning to learn the historical browsing operation data to obtain the supply and demand correlation model to determine the correlation between the object supply side and the object demand side. When the information processing device obtains different object attributes, the information processing device can still use the supply and demand correlation model to obtain the accurate correlation between the object supply side and the object demand side, thereby improving the accuracy of the determined supply and demand relationship. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 A flow chart of an information processing method provided in an embodiment of the present application;

[0017] Figure 2 An exemplary information processing block diagram provided for an embodiment of the present application;

[0018] Figure 3 An exemplary schematic diagram of a supply-demand relationship matching system based on unsupervised learning provided in an embodiment of the present application;

[0019] Figure 4 A schematic diagram of the structure of an information processing device provided in an embodiment of the present application Figure 1 ;

[0020] Figure 5 A schematic diagram of the structure of an information processing device provided in an embodiment of the present application Figure 2 . DETAILED DESCRIPTION

[0021] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. It should be understood that the specific embodiments described here are only used to explain the present application and are not used to limit the present application.

[0022] In the prior art, a static service supply and demand matching pattern extraction method for large services uses strict logical operations to compare and match the supply and demand details one by one, ignoring the importance differences between different functional points and the differences in attention between different users when making manual selections. The technical solution of the enterprise recommendation method and application server only considers the supply and demand relationship from the perspective of the enterprise, without breaking down into specific needs and goods, and does not fundamentally solve the problems faced by this scenario; and the solution uses artificially designed tags to mark the keyword features of different enterprises, which requires more human intervention and judgment.

[0023] The problems existing in the prior art can be solved by using the information processing method in the first embodiment.

[0024] Embodiment 1

[0025] The present application provides an information processing method, which is applied to an information processing device. Figure 1 A flow chart of an information processing method provided in an embodiment of the present application, such as Figure 1 As shown, the information processing method may include:

[0026] S101, acquiring first historical operation data associated with an object at an object demand side, and acquiring second historical operation data associated with an object at an object supply side; acquiring object attributes at the object supply side and demand attributes at the object demand side.

[0027] An information processing method provided in an embodiment of the present application is applicable to a scenario in which the correlation between an object supply side and an object demand side is determined.

[0028] In the embodiments of the present application, the information processing device can be implemented in various forms. For example, the information processing device described in the present application may include devices such as mobile phones, cameras, tablet computers, laptop computers, PDAs, portable media players (PMPs), navigation devices, wearable devices, smart bracelets, pedometers, and devices such as digital TVs, desktop computers, and servers.

[0029] In the embodiment of the present application, the object may be goods (commodity), the object may be express delivery, or the object may be other things. The specific object can be determined according to the actual situation, and the embodiment of the present application does not limit this.

[0030] In the embodiment of the present application, if the object is a product, the object demand side may be a product demand side, and specifically the product demand side may be a retailer's demand for the product; the product may be a product that can be supplied by a supplier.

[0031] It should be noted that obtaining the first historical operation data associated with the object at the object demand side may be obtaining the first historical operation data associated with the goods at the goods demand side (demand side); and obtaining the second historical operation data associated with the object at the object supply side may be obtaining the second historical operation data associated with the goods at the goods supply side (supplier side).

[0032] Specifically, the product may be a historical product, and the product demand may be a historical product demand.

[0033] It should also be noted that the product supply end can be a product supply webpage related to the provision of products; the product demand end can be a webpage related to the product demand information input by retailers and / or the demand information purchased, browsed, and consulted by suppliers.

[0034] In the embodiment of the present application, the number of attributes of the object attributes can be one, the number of attributes can be two, or the number of attributes can be more than one. The specific number of attributes of the object attributes can be determined according to actual conditions, and the embodiment of the present application does not limit this.

[0035] In the embodiment of the present application, the number of attributes of the requirement attributes can be one, the number of attributes of the requirement attributes can be two, or the number of attributes of the requirement attributes can be multiple. The specific number of attributes of the requirement attributes can be determined based on actual conditions, and the embodiment of the present application does not limit this.

[0036] In an embodiment of the present application, if the object is a product, the object attributes include one of the following attributes: product price, product quantity, product location, logistics cost, brand regional penetration, regional price control, government and enterprise endorsement, funding capacity, pre-deposit amount, supply chain finance intake, etc.

[0037] In an embodiment of the present application, the demand attributes include one of the following attributes: price of the demanded goods, quantity of the demanded goods, location of the demanded goods, logistics cost of the demanded goods, regional brand penetration of the demanded goods, regional price control of the demanded goods, government and enterprise endorsement of the demanded goods, funding capacity of the demanded goods, pre-deposit amount of the demanded goods, supply chain finance intake of the demanded goods, etc.

[0038] It should be noted that the number of attributes of the object attributes and the number of attributes of the requirement attributes can be the same; the number of attributes of the object attributes and the number of attributes of the requirement attributes can also be different; the specific number can be determined according to actual conditions, and the embodiments of the present application do not limit this.

[0039] In an embodiment of the present application, the information processing device may first obtain the first historical data of the retailer (demand side) and the second historical data of the supplier (supply side); then the information processing device filters out the first historical operation data from the first historical data; and the information processing device filters out the second historical operation data from the second historical data.

[0040] In the embodiment of the present application, the first historical data may be all historical operation data that the retailer has operated on the commodity trading platform; the second historical data may be all historical operation data that the supplier has operated on the commodity trading platform.

[0041] It should be noted that the trading platform may be a certain trading platform; the trading platform may also be all trading platforms existing in a certain trading environment, and the specific one may be determined according to the actual situation, and the embodiments of the present application do not limit this.

[0042] In the embodiment of the present application, the first historical operation data and the second historical operation data acquired by the information processing device can be expressed by formula (1) and formula (2):

[0043]

[0044]

[0045] in, Represents the demand side of goods α Get the goods supply side i The associated operation vector (the first historical operation data), μ represents the supplier’s click, favorite, browse, purchase and other data; Represents the supply side of goods i Get the information related to product demand α The associated operation vector (second historical operation data), μ' represents the retailer's click, collection, browse, message and other data; Q represents the number of attributes of the two types of data.

[0046] In the embodiment of the present application, based on the module lengths of the two operation vectors corresponding to the first historical operation data and the second historical operation data, the product s can be calculated respectively. i and product demand α The degree of forward and reverse matching between them is shown in formula (3) and formula (4):

[0047]

[0048]

[0049] Among them, d(s i ,r α) represents the demand for goods from the perspective of the supplier. α With goods i The degree of matching, d(r α ,s i ) represents the perspective of the demand side (retailer), the product s i Its demand α degree of match.

[0050] S102. Input the first historical operation data, the second historical operation data, the object attributes and the demand attributes into the supply and demand correlation model to obtain the correlation between the object supply side and the object demand side, so as to find the target demand corresponding to the object supply side in the object demand side based on the correlation, or find the target object supply side related to the object demand side in the object supply side; the supply and demand correlation model is a model obtained by learning the historical browsing operation data through unsupervised learning.

[0051] In an embodiment of the present application, an information processing device obtains first historical operation data associated with an object at an object demand side and obtains second historical operation data associated with an object at an object supply side; after obtaining the object attributes at the object supply side and the demand attributes at the object demand side, the information processing device can input the first historical operation data, the second historical operation data, the object attributes and the demand attributes into a supply and demand correlation model to obtain the correlation between the object supply side and the object demand side.

[0052] In an embodiment of the present application, the number of object supply ends is at least two; the number of object demand ends is at least two; the information processing device inputs the first historical operation data, the second historical operation data, the object attributes and the demand attributes into the supply and demand correlation model to obtain the correlation between the object supply end and the object demand end, including: the information processing device uses the supply and demand correlation model to perform spatial clustering processing on the object attributes to obtain a first correlation between at least two object supply ends; the information processing device uses the supply and demand correlation model to perform spatial clustering processing on the demand attributes to obtain a second correlation between at least two object demand ends; the information processing device uses the supply and demand correlation model to associate the first correlation and the second correlation according to the first historical operation data and the second historical operation data to obtain the correlation.

[0053] In the embodiment of the present application, the number of objects at the at least two object supply ends can be two or more, and the specific number of goods can be determined according to actual conditions, which is not limited in the embodiment of the present application.

[0054] In the embodiment of the present application, the number of demands of at least two object demand ends can be two or more. The specific number of demands can be determined according to actual conditions, and the embodiment of the present application does not limit this.

[0055] In an embodiment of the present application, an information processing device uses a supply and demand correlation model to perform spatial clustering processing on object attributes to obtain a first correlation between at least two object supply ends, including: the information processing device determines the object attribute weight corresponding to the object attribute; and uses the supply and demand correlation model to convert the object attribute weight into at least two object attribute vectors corresponding to at least two object supply ends; the information processing device normalizes the at least two object attribute vectors to obtain at least two processed object attribute vectors; the information processing device determines a first distance between at least two processed object attribute vectors, and uses the first distance as the first correlation.

[0056] In an embodiment of the present application, a correspondence between preset object attributes and preset attribute weights is configured in the information processing device. The information processing device can determine the object attribute weight corresponding to the object attribute based on the correspondence between the preset object attributes and the preset attribute weights.

[0057] In the embodiment of the present application, the correspondence between the preset object attributes and the preset attribute weights is the correspondence configured in the information processing device; the correspondence between the preset object attributes and the preset attribute weights may also be the correspondence received in advance by the information processing device; the correspondence between the preset object attributes and the preset attribute weights may also be the correspondence obtained by the information processing device in other ways, which can be determined according to actual conditions, and the embodiment of the present application does not limit this.

[0058] In an embodiment of the present application, the information processing device determines the object attribute weight corresponding to the object attribute based on the correspondence between the preset object attributes and the preset attribute weights. The process can be that the information processing device searches for the first preset object attribute corresponding to the object attribute in the correspondence between the preset object attributes and the preset attribute weights, and determines the first preset attribute weight corresponding to the first preset object attribute in the correspondence between the preset object attributes and the preset attribute weights, and uses the first preset attribute weight as the object attribute weight.

[0059] In an embodiment of the present application, the process in which the information processing device normalizes at least two object attribute vectors to obtain at least two processed object attribute vectors can be that the information processing device uses an activation function to normalize at least two object attribute vectors to obtain at least two processed object attribute vectors; the information processing device can also use other methods to normalize at least two object attribute vectors to obtain at least two processed object attribute vectors; the specific method can be determined according to actual conditions, and the embodiment of the present application is not limited to this.

[0060] It should be noted that the activation function may be a Sigmoid function, or other functions that have the function of normalizing at least two object attribute vectors. The specific function may be determined according to actual conditions, and the embodiments of the present application do not limit this.

[0061] It should be noted that each element of the at least two processed object attribute vectors obtained by the information processing device may be a value between 0 and 1.

[0062] In an embodiment of the present application, the process of an information processing device determining the first distance between at least two processed object attribute vectors can be that the information processing device maps at least two processed object attribute vectors into a feature space to obtain at least two coordinate points corresponding to the at least two processed object attribute vectors, and the information processing device obtains the first distance by determining the distance between each two coordinate points of the at least two coordinate points.

[0063] In an embodiment of the present application, the information processing device uses a supply and demand correlation model to perform spatial clustering processing on demand attributes to obtain a second correlation between at least two object demand ends, including: the information processing device determines the demand attribute weight corresponding to the demand attribute; and uses the supply and demand correlation model to convert the demand attribute weight into at least two demand attribute vectors corresponding to at least two object demand ends; the information processing device normalizes the at least two demand attribute vectors to obtain at least two processed demand attribute vectors; the information processing device determines the second distance between the at least two processed demand attribute vectors, and uses the second distance as the second correlation.

[0064] In an embodiment of the present application, a correspondence between preset requirement attributes and preset attribute weights is configured in the information processing device. The information processing device can determine the requirement attribute weight corresponding to the requirement attribute based on the correspondence between the preset requirement attributes and the preset attribute weights.

[0065] In the embodiment of the present application, the correspondence between the preset requirement attributes and the preset attribute weights is the correspondence configured in the information processing device; the correspondence between the preset requirement attributes and the preset attribute weights may also be the correspondence received by the information processing device; the correspondence between the preset requirement attributes and the preset attribute weights may also be the correspondence obtained by the information processing device in other ways, which may be determined according to actual conditions, and the embodiment of the present application does not limit this.

[0066] In an embodiment of the present application, the process of the information processing device determining the requirement attribute weight corresponding to the requirement attribute based on the correspondence between the preset requirement attributes and the preset attribute weights can be that the information processing device searches for the first preset requirement attribute corresponding to the requirement attribute in the correspondence between the preset requirement attributes and the preset attribute weights, and determines the first preset weight corresponding to the first preset requirement attribute in the correspondence between the preset requirement attributes and the preset attribute weights, and uses the first preset weight as the requirement attribute weight.

[0067] In an embodiment of the present application, the process in which the information processing device normalizes at least two demand attribute vectors to obtain at least two processed demand attribute vectors can be that the information processing device uses an activation function to normalize at least two demand attribute vectors to obtain at least two processed demand attribute vectors; the information processing device can also use other methods to normalize at least two demand attribute vectors to obtain at least two processed demand attribute vectors; the specific method can be determined according to actual conditions, and the embodiment of the present application is not limited to this.

[0068] It should be noted that each element of the at least two processed demand attribute vectors obtained by the information processing device may be a value between 0 and 1.

[0069] In an embodiment of the present application, the process of the information processing device determining the second distance between at least two processed demand attribute vectors can be that the information processing device maps the at least two processed demand attribute vectors into the feature space to obtain at least two coordinate points corresponding to the at least two processed demand attribute vectors, and the information processing device obtains the second distance by determining the distance between each two coordinate points of the at least two coordinate points.

[0070] In the embodiment of the present application, after the information processing device obtains the object attribute of the object supply side and the demand attribute of the object demand side, and determines the object attribute weight corresponding to the object attribute and the demand attribute weight corresponding to the demand attribute, the information processing device can use the supply and demand correlation model to convert the object attribute weight into at least two object attribute vectors corresponding to at least two object supply sides, and use the supply and demand correlation model to convert the demand attribute weight into at least two demand attribute vectors corresponding to the at least two object demand sides. Specifically, at least two object attribute vectors can constitute an object set (goods set) At least two requirement attribute vectors can constitute a requirement set Among them, the goods are set to s i (i∈1~N), N is the total quantity of goods, and the demand is set to r α (α∈1~M), M is the total demand, among which s i and r αThe vector representation of is shown in formula (5) and formula (6):

[0071]

[0072]

[0073] It should be noted that P represents the number of attributes of goods and demand, x i Represents the original value of each attribute of the i-th item (object attribute weight), y α Represents the original value of each attribute of the αth requirement (requirement attribute weight).

[0074] In the embodiment of the present application, in order to balance the difference in the range of the attribute values ​​of the goods and the demand for goods, the object attribute weight and the demand attribute weight can be standardized (normalized), and the values ​​can be normalized to the range of 0 to 1 using an activation function. Exemplary: the object attribute vector is normalized, and the object attribute vector obtained is shown in formula (7); the demand attribute vector is normalized, and the demand attribute vector obtained is shown in formula (8):

[0075]

[0076]

[0077] Among them, x′ i and y′ α They are the standardized object attribute vector and the standardized demand attribute vector respectively. The corresponding at least two processed object attribute vectors are shown in formula (9); the corresponding at least two processed demand attribute vectors are shown in formula (10):

[0078]

[0079]

[0080] In the embodiment of the present application, at least two processed object attribute vectors are mapped into the first feature space to obtain at least two coordinate points, and the Euclidean distance (first distance) between any two points can represent the first correlation between at least two object supply ends, as shown in formula (11); at least two processed demand attribute vectors are mapped into the second feature space to obtain at least two coordinate points, and the Euclidean distance (second distance) between any two points can represent the second correlation between at least two object demand ends, as shown in formula (12):

[0081]

[0082]

[0083] Among them, d(s i ,s j ) represents i and j The correlation between two goods (object supply ends), d(r α ,r β ) represents r α and r β The correlation between two requirements (object requirement sides).

[0084] In the embodiment of the present application, after the information processing device obtains the first historical operation data, the second historical operation data, the first correlation and the second correlation, the information processing device can use the supply and demand correlation model to associate the first correlation and the second correlation according to the first historical operation data and the second historical operation data to obtain the correlation. Specifically, the information processing device uses the supply and demand correlation model to associate the first correlation and the second correlation according to the first historical operation data and the second historical operation data to cover all supply and demand relationships with limited user operation data, and the manner of obtaining the correlation is shown in formula (13) and formula (14):

[0085]

[0086]

[0087] It should be noted that the first half of formula (13) and formula (14) represent the direct correlation obtained directly through user behavior, while the second half represents the indirect correlation obtained through the correlation between demand and goods.

[0088] In an embodiment of the present application, the information processing device inputs the first historical operation data, the second historical operation data, the object attributes and the demand attributes into the supply and demand correlation model. After obtaining the correlation between the object supply side and the object demand side, the information processing device will also establish a correlation list between the object supply side and the object demand side based on the correlation; the information processing device displays the correlation list for the client to select the target object demand side corresponding to the object supply side according to the correlation list, or select the target object supply side related to the object demand side according to the correlation list.

[0089] In the embodiment of the present application, the information processing device can obtain a product set Each product i , corresponding to the demand set Each requirement r α The supply-demand matching degree is obtained by arranging the matching degrees in descending order. Similarly, the information processing device can also obtain the supply-demand correspondence with the highest matching degree. α For each producti The supply-demand correspondence with the highest matching degree.

[0090] In an embodiment of the present application, the information processing device can also manually associate the object supply side (supply of goods) and the object demand side (goods demand) through manual labeling, so as to convert the unsupervised task into a fully supervised task, and train the feature extraction network through machine learning.

[0091] For example, an information processing block diagram is as follows: Figure 2 As shown: the information processing device obtains at least two object attributes of at least two object supply ends and at least two demand attributes of at least two object demand ends. The information processing device determines the object attribute weight corresponding to the object attribute; and uses the supply and demand correlation model to convert the object attribute weight into at least two object attribute vectors corresponding to at least two object supply ends; the information processing device determines the demand attribute weight corresponding to the demand attribute; and uses the supply and demand correlation model to convert the demand attribute weight into at least two demand attribute vectors corresponding to at least two object demand ends. The information processing device normalizes the at least two object attribute vectors to obtain at least two processed object attribute vectors; and determines the first distance between the at least two processed object attribute vectors, and uses the first distance as the first correlation; the information processing device normalizes the at least two demand attribute vectors to obtain at least two processed demand attribute vectors; determines the second distance between the at least two processed demand attribute vectors, and uses the second distance as the second correlation. The information processing device obtains the first historical operation data associated with the object at the object demand end, and obtains the second historical operation data associated with the object at the object supply end. The information processing device associates the first correlation and the second correlation using the first historical operation data and the second historical operation data to obtain the correlation between the object supply end and the object demand end. The information processing device establishes and displays the correlation list between the object supply end and the object demand end according to the correlation.

[0092] It should be noted that the correlation includes the correlation between the object demand side and the object supply side and the correlation between the object supply side and the object demand side. The correlation list includes the correlation list between the object demand side and the object supply side and the correlation list between the object supply side and the object demand side.

[0093] In an embodiment of the present application, the information processing device may use the second historical operation data to associate the first correlation to obtain the correlation between the object demand side and the object supply side; the information processing device may use the first historical operation data to associate the second correlation to obtain the correlation between the object supply side and the object demand side. The information processing device establishes a correlation list between the object demand side and the object supply side based on the correlation between the object demand side and the object supply side; the information processing device establishes a correlation between the object supply side and the object demand side based on the correlation between the object supply side and the object demand side.

[0094] For example, the schematic diagram of the supply and demand relationship matching system based on unsupervised learning in the embodiment of the present application is as follows: Figure 3 As shown: the information processing device obtains the object attribute of the object supply side at the supplier (supplier) and obtains the demand attribute of the object demand side at the demand side (retailer); the information processing device determines the object attribute weight corresponding to the object attribute; and uses the supply and demand correlation model to convert the object attribute weight into at least two object attribute vectors corresponding to at least two object supply sides; normalizes the at least two object attribute vectors to obtain at least two processed object attribute vectors; determines the first distance between the at least two processed object attribute vectors, and uses the first distance as the first correlation. The information processing device determines the demand attribute weight corresponding to the demand attribute; and uses the supply and demand correlation model to convert the demand attribute weight into at least two demand attribute vectors corresponding to at least two object demand sides; normalizes the at least two demand attribute vectors to obtain at least two processed demand attribute vectors; determines the second distance between the at least two processed demand attribute vectors, and uses the second distance as the second correlation. The information processing device obtains the first historical operation data corresponding to the supplier account; obtains the second historical operation data corresponding to the demand side account, and then uses the supply and demand correlation model to associate the first correlation and the second correlation according to the first historical operation data and the second historical operation data to obtain the correlation between the object supply side and the object demand side.

[0095] It can be understood that the information processing device determines the correlation between the object supply side and the object demand side by inputting the first historical operation data, the second historical operation data, the object attributes and the demand attributes into the supply and demand correlation model, and using unsupervised learning to learn the historical browsing operation data to obtain the supply and demand correlation model. This allows the information processing device to determine the correlation between the object supply side and the object demand side when acquiring different object attributes. The information processing device can still use the supply and demand correlation model to obtain the accurate correlation between the object supply side and the object demand side, thereby improving the accuracy of the determined supply and demand relationship.

[0096] Embodiment 2

[0097] Based on the same inventive concept of the first embodiment, the embodiment of the present application provides an information processing device 1, corresponding to an information processing method; Figure 4 A schematic diagram of the structure of an information processing device provided in an embodiment of the present application Figure 1 , the information processing device 1 may include:

[0098] An acquisition unit 11 is used to acquire first historical operation data associated with an object at an object demand side, and to acquire second historical operation data associated with the object at an object supply side; and to acquire object attributes at the object supply side and demand attributes at the object demand side;

[0099] The input unit 12 is used to input the first historical operation data, the second historical operation data, the object attributes and the demand attributes into a supply and demand correlation model to obtain the correlation between the object supply end and the object demand end, so as to search the target demand corresponding to the object supply end in the object demand end based on the correlation, or to search the target object supply end related to the object demand end in the object supply end; the supply and demand correlation model is a model obtained by learning historical browsing operation data through unsupervised learning.

[0100] In some embodiments of the present application, the number of the object supply ends is at least two; the number of the object demand ends is at least two; the device further includes a processing unit and an association unit;

[0101] The processing unit is used to perform spatial clustering processing on the object attributes using the supply-demand correlation model to obtain a first correlation between at least two object supply ends; and perform spatial clustering processing on the demand attributes using the supply-demand correlation model to obtain a second correlation between at least two object demand ends;

[0102] The association unit is used to associate the first correlation and the second correlation with the first historical operation data and the second historical operation data by using the supply-demand correlation model to obtain the correlation.

[0103] In some embodiments of the present application, the device further comprises a determination unit and a conversion unit;

[0104] The determining unit is configured to determine an object attribute weight corresponding to the object attribute; determine a first distance between the at least two processed object attribute vectors, and use the first distance as the first correlation;

[0105] The conversion unit is used to convert the object attribute weight into at least two object attribute vectors corresponding to the at least two object supply ends by using the supply-demand correlation model;

[0106] The processing unit is used to perform normalization processing on the at least two object attribute vectors to obtain at least two processed object attribute vectors.

[0107] In some embodiments of the present application, the determining unit is used to determine the demand attribute weight corresponding to the demand attribute; determine a second distance between the at least two processed demand attribute vectors, and use the second distance as the second correlation;

[0108] The conversion unit is used to convert the demand attribute weight into at least two demand attribute vectors corresponding to the at least two object demand ends by using the supply and demand correlation model;

[0109] The processing unit is used to perform normalization processing on the at least two demand attribute vectors to obtain at least two processed demand attribute vectors.

[0110] In some embodiments of the present application, the apparatus further comprises an establishing unit and a display unit;

[0111] The establishing unit is used to establish a correlation list between the object supply end and the object demand end according to the correlation;

[0112] The display unit is used to display the correlation list so that the client can select the target object demand side corresponding to the object supply side according to the correlation list, or select the target object supply side related to the object demand side according to the correlation list.

[0113] It should be noted that, in actual applications, the above-mentioned acquisition unit 11 and input unit 12 can be implemented by a processor 13 on the information processing device 1, specifically a CPU (Central Processing Unit), an MPU (Microprocessor Unit), a DSP (Digital Signal Processing) or a field programmable gate array (FPGA); the above-mentioned data storage can be implemented by a memory 14 on the information processing device 1.

[0114] The present application also provides an information processing device 1, such as Figure 5 As shown, the information processing device 1 includes: a processor 13, a memory 14 and a communication bus 15. The memory 14 communicates with the processor 13 via the communication bus 15. The memory 14 stores a program executable by the processor 13. When the program is executed, the information processing method described above is executed by the processor 13.

[0115] In practical applications, the memory 14 may be a volatile memory, such as a random access memory (RAM); or a non-volatile memory, such as a read-only memory (ROM), a flash memory, a hard disk (HDD) or a solid-state drive (SSD); or a combination of the above types of memory, and provide instructions and data to the processor 13.

[0116] An embodiment of the present application provides a computer-readable storage medium having a computer program thereon, and when the program is executed by the processor 13, the information processing method as described above is implemented.

[0117] It can be understood that the information processing device determines the correlation between the object supply side and the object demand side by inputting the first historical operation data, the second historical operation data, the object attributes and the demand attributes into the supply and demand correlation model, and using unsupervised learning to learn the historical browsing operation data to obtain the supply and demand correlation model. This allows the information processing device to determine the correlation between the object supply side and the object demand side when acquiring different object attributes. The information processing device can still use the supply and demand correlation model to obtain the accurate correlation between the object supply side and the object demand side, thereby improving the accuracy of the determined supply and demand relationship.

[0118] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of hardware embodiments, software embodiments, or embodiments in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage and optical storage, etc.) that contain computer-usable program code.

[0119] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1A device that provides the functions specified in a block or multiple blocks.

[0120] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0121] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0122] The above description is only a preferred embodiment of the present application and is not intended to limit the protection scope of the present application.

Claims

1. An information processing method, characterized in that: The method comprises: Acquire the first historical operation data associated with the object at the object demand side, and acquire the second historical operation data associated with the object at the object supply side; acquire the object attribute of the object supply side and the demand attribute of the object demand side; the first historical operation data is the data screened from all the historical operation data operated by the retailer on the commodity trading platform, and the second historical operation data is the data screened from all the historical operation data operated by the supplier on the commodity trading platform; The first historical operation data, the second historical operation data, the object attribute and the demand attribute are input into a supply-demand correlation model to obtain the correlation between the object supply end and the object demand end, so as to search the object demand end for the target demand corresponding to the object supply end, or search the object supply end for the target object supply end related to the object demand end, based on the correlation; the supply-demand correlation model is a model obtained by learning the historical browsing operation data through unsupervised learning; The step of inputting the first historical operation data, the second historical operation data, the object attribute and the demand attribute into a supply-demand correlation model to obtain the correlation between the object supply end and the object demand end includes: Performing spatial clustering processing on the object attributes using the supply-demand correlation model to obtain a first correlation between at least two object supply ends; Performing spatial clustering processing on the demand attributes using the supply-demand correlation model to obtain a second correlation between at least two object demand ends; The first correlation and the second correlation are associated with each other according to the first historical operation data and the second historical operation data by using the supply-demand correlation model to obtain the correlation.

2. The method according to claim 1, characterized in that The number of the object supply ends is at least two; the number of the object demand ends is at least two.

3. The method according to claim 2, characterized in that The using the supply-demand correlation model to perform spatial clustering processing on the object attributes to obtain a first correlation between at least two object supply ends includes: Determining object attribute weights corresponding to the object attributes; and converting the object attribute weights into at least two object attribute vectors corresponding to the at least two object supply ends using the supply-demand correlation model; Normalizing the at least two object attribute vectors to obtain at least two processed object attribute vectors; A first distance between the at least two processed object attribute vectors is determined, and the first distance is used as the first correlation.

4. The method according to claim 2, characterized in that: The using the supply-demand correlation model to perform spatial clustering processing on the demand attributes to obtain a second correlation between at least two object demand ends includes: Determining a demand attribute weight corresponding to the demand attribute; and converting the demand attribute weight into at least two demand attribute vectors corresponding to the at least two object demand ends using the supply-demand correlation model; Normalizing the at least two demand attribute vectors to obtain at least two processed demand attribute vectors; A second distance between the at least two processed demand attribute vectors is determined, and the second distance is used as the second correlation.

5. The method according to claim 1, characterized in that After inputting the first historical operation data, the second historical operation data, the object attribute and the demand attribute into a supply-demand correlation model to obtain the correlation between the object supply end and the object demand end, the method further includes: Establishing a correlation list between the object supply end and the object demand end according to the correlation; The correlation list is displayed so that the client can select the target object demand side corresponding to the object supply side according to the correlation list, or select the target object supply side related to the object demand side according to the correlation list.

6. An information processing device, characterized in that: The device comprises: An acquisition unit is used to acquire first historical operation data associated with an object at an object demand side, and to acquire second historical operation data associated with the object at an object supply side; to acquire object attributes at the object supply side and demand attributes at the object demand side; the first historical operation data is data screened from all historical operation data operated by a retailer on a commodity trading platform, and the second historical operation data is data screened from all historical operation data operated by a supplier on a commodity trading platform; an input unit, configured to input the first historical operation data, the second historical operation data, the object attribute and the demand attribute into a supply-demand correlation model, to obtain the correlation between the object supply end and the object demand end, so as to search the object demand end for a target demand corresponding to the object supply end, or to search the object supply end for a target object supply end related to the object demand end, based on the correlation; the supply-demand correlation model is a model obtained by learning the historical browsing operation data through unsupervised learning; A processing unit, configured to perform spatial clustering processing on the object attributes using the supply-demand correlation model to obtain a first correlation between at least two object supply ends; and perform spatial clustering processing on the demand attributes using the supply-demand correlation model to obtain a second correlation between at least two object demand ends; A correlation unit is used to use the supply-demand correlation model to correlate the first correlation and the second correlation according to the first historical operation data and the second historical operation data to obtain the correlation.

7. The device according to claim 6, characterized in that The number of the object supply ends is at least two; the number of the object demand ends is at least two.

8. The device according to claim 7, characterized in that The device also includes a determination unit and a conversion unit; The determining unit is configured to determine an object attribute weight corresponding to the object attribute; determine a first distance between the at least two processed object attribute vectors, and use the first distance as the first correlation; The conversion unit is used to convert the object attribute weight into at least two object attribute vectors corresponding to the at least two object supply ends by using the supply-demand correlation model; The processing unit is used to perform normalization processing on the at least two object attribute vectors to obtain at least two processed object attribute vectors.

9. An information processing device, characterized in that: The device comprises: A memory, a processor and a communication bus, wherein the memory communicates with the processor via the communication bus, the memory stores an information processing program executable by the processor, and when the information processing program is executed, the method according to any one of claims 1 to 5 is performed by the processor.

10. A storage medium having a computer program stored thereon, applied to an information processing device, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 5 is implemented.

Images