Information processing method and device, electronic equipment and storage medium

Abstract

The present disclosure provides an information processing method, device, electronic equipment and storage medium. The method comprises: obtaining procurement demand information and procurement item knowledge graph; performing entity extraction on the procurement demand information to obtain procurement demand entities; querying attribute entities of a plurality of items from the procurement item knowledge graph; and matching the procurement demand entities and the attribute entities of the plurality of items to obtain a target item list corresponding to the procurement demand information. The method can automatically and accurately obtain a target item list corresponding to the procurement demand information, improve the accuracy of matching procurement demand and target items, and thus improve procurement efficiency.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of information processing, and particularly relates to an information processing method and device, electronic equipment and storage medium. BACKGROUND

[0002] In an e-commerce purchasing scenario, when an enterprise purchases materials, a purchasing personnel needs to select goods meeting the purchasing demand of the enterprise from a large number of goods.

[0003] In the related art, the purchasing personnel sets a screening condition according to his own experience, and finds goods from a large number of goods pools. This method has subjective factors, and the purchasing accuracy is low. Moreover, a large amount of manpower is consumed, and the purchasing efficiency is low.

[0004] It should be noted that the information disclosed in the above background section is only used to strengthen the understanding of the background of the present disclosure, and therefore can include information that does not constitute prior art known to those of ordinary skill in the art. SUMMARY

[0005] The purpose of the present disclosure is to provide an information processing method, device, electronic equipment and storage medium, which can automatically and accurately obtain a target item list corresponding to purchasing demand information, improve the accuracy of matching of purchasing demand and target items, and thus improve the purchasing efficiency.

[0006] Other characteristics and advantages of the present disclosure will become apparent from the following detailed description, or will be learned by practice of the present disclosure.

[0007] An information processing method is provided in the embodiments of the present disclosure, including: obtaining purchasing demand information and a purchasing item knowledge graph; performing entity extraction on the purchasing demand information to obtain purchasing demand entities; querying attribute entities of a plurality of items from the purchasing item knowledge graph; and matching the purchasing demand entities and the attribute entities of the plurality of items to obtain a target item list corresponding to the purchasing demand information.

[0008] In some example embodiments of the present disclosure, the entity extraction on the purchasing demand information to obtain purchasing demand entities includes: labeling the purchasing demand information by a sequence labeling model to obtain a label sequence of the purchasing demand information; and extracting the purchasing demand entities from the purchasing demand information according to labels in the label sequence.

[0009] In some example embodiments of the present disclosure, the method further includes: obtaining user behavior data of a purchaser; analyzing the user behavior data by a context relationship to obtain purchasing background information of the purchaser; and compensating the purchasing demand entities according to the purchasing background information to update the purchasing demand entities.

[0010] In some example embodiments of the present disclosure, matching the procurement demand entity and the attribute entities of the plurality of items to obtain a target item list corresponding to the procurement demand information comprises: determining a text similarity of the procurement demand entity and the attribute entities of the plurality of items; determining, according to the text similarity, a target attribute entity matching the procurement demand entity from the attribute entities; and determining at least one target item according to the target attribute entity to compose the target item list.

[0011] In some example embodiments of the present disclosure, determining at least one target item according to the target attribute entity to compose the target item list comprises: determining a matching degree of each target item and the procurement demand information; obtaining price attribute information and public opinion attribute information of each target item; and determining, according to the matching degree of each target item and the procurement demand information, the price attribute information and the public opinion attribute information, a target push item from the at least one target item to compose the target item list.

[0012] In some example embodiments of the present disclosure, the method further comprises: obtaining original data, the original data comprising item data, supplier data and network public opinion data; performing entity extraction on the item data, the supplier data and the network public opinion data respectively to obtain item attribute entities, supplier attribute entities and network public opinion entities; and constructing the procurement item knowledge graph according to the item attribute entities, the supplier attribute entities and the network public opinion entities.

[0013] In some example embodiments of the present disclosure, the method further comprises: obtaining a selected item selected by a procurement party from the target item list; constructing a triple relationship according to the selected item and the procurement demand entity and storing to the procurement item knowledge graph.

[0014] Embodiments of the present disclosure provide an information processing apparatus, comprising: an obtaining module configured to obtain procurement demand information and a procurement item knowledge graph; an obtaining module configured to perform entity extraction on the procurement demand information to obtain a procurement demand entity; a querying module configured to query a plurality of item attribute entities from the procurement item knowledge graph; and a matching module configured to match the procurement demand entity and the plurality of item attribute entities to obtain a target item list corresponding to the procurement demand information.

[0015] Embodiments of the present disclosure provide an electronic device, comprising: at least one processor; a storage apparatus configured to store at least one program, when the at least one program is executed by the at least one processor, causing the at least one processor to implement any of the above information processing methods.

[0016] The embodiment of the present disclosure provides a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement any one of the information processing methods.

[0017] The information processing method provided by some embodiments of the present disclosure can automatically and accurately obtain a target item list corresponding to the procurement demand information by performing entity extraction on the procurement demand information to obtain procurement demand entities, querying attribute entities of a plurality of items from a procurement item knowledge graph, and matching the procurement demand entities and the attribute entities of the items, thereby improving the accuracy of matching the procurement demand and the target items and improving the procurement efficiency. In addition, the method can save the workload of manual query, search and matching, save the operation steps and procurement time of the procurement party, and thus improve the user experience.

[0018] It should be understood that the foregoing general description and the following detailed description are only exemplary and explanatory, and cannot limit the present disclosure. BRIEF DESCRIPTION OF DRAWINGS

[0019] The accompanying drawings incorporated in and forming a part of the specification illustrate embodiments consistent with the present disclosure and serve to explain the principles of the present disclosure. It is apparent that the accompanying drawings in the following description are only some embodiments of the present disclosure, and other drawings can be obtained by those of ordinary skill in the art without creative labor on the basis of these drawings.

[0020] Figure 1 A schematic diagram of an exemplary system architecture to which the information processing method of the embodiments of the present disclosure can be applied is shown.

[0021] Figure 2 is a flowchart of an information processing method according to an exemplary embodiment.

[0022] Figure 3 is a schematic diagram of procurement demand information and extraction of the procurement demand information into procurement demand entities according to an example.

[0023] Figure 4 is a schematic diagram of matching procurement demand entities and attribute entities of goods according to an example.

[0024] Figure 5 is a schematic diagram of a demand matching degree scoring model according to an example.

[0025] Figure 6 is a flowchart of another information processing method according to an exemplary embodiment.

[0026] Figure 7is a schematic diagram of constructing a procurement item knowledge graph according to an example.

[0027] Figure 8 is a schematic diagram of an information processing system according to an example.

[0028] Figure 9 is a block diagram of an information processing apparatus according to an example embodiment.

[0029] Figure 10 is a structural schematic diagram of an electronic device according to an example embodiment. DETAILED DESCRIPTION

[0030] Example embodiments now will be described more fully hereinafter with reference to the accompanying drawings. Example embodiments, however, can be implemented in many different forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of example embodiments to those skilled in the art. Features, structures or characteristics described in connection with one embodiment can be combined in any suitable manner with features, structures or characteristics of another embodiment.

[0031] In addition, the accompanying drawings are included to provide a further understanding of the present disclosure and are incorporated in and constitute a part of this specification. The drawings illustrate embodiments of the present disclosure and, together with the description, serve to explain the principles of the present disclosure. In the drawings:

[0032] In the present disclosure, unless specifically defined otherwise, the terms "mounting", "connection", "connecting", "fixed", and the like, should be given a broad meaning, for example, can be fixed connection, can be detachable connection, or can be integrated; can be mechanical connection, can be electrical connection, or can be communication with each other; can be directly connected, or can be indirectly connected through an intermediate medium; can be internal connection of two elements or interaction relationship between two elements. For those skilled in the art, the specific meaning of the above terms in the present disclosure can be understood according to the specific circumstances.

[0033] In addition, in the description of the present disclosure, the meaning of "a plurality of" is at least two, for example, two, three, etc., unless otherwise explicitly and specifically limited. The terms "first", "second" are only for descriptive purposes, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, the features limited by "first", "second" can explicitly or implicitly include one or more of the features.

[0034] Figure 1 A schematic diagram showing an exemplary system architecture to which the information processing method of the embodiments of the present disclosure can be applied is shown.

[0035] As Figure 1 shown, the system architecture can include a server 101, a network 102, and a terminal device 103. The network 102 is a medium to provide a communication link between the terminal device 103 and the server 101. The network 102 can include various connection types, such as wired, wireless communication links, or fiber optic cables, and the like.

[0036] The server 101 can be a server that provides various services, such as a background management server that provides support for the operation of a device by a user using the terminal device 103. The background management server can analyze and process received request data and the like, and feed back the processing result to the terminal device 103.

[0037] In the embodiments of the present disclosure, the server 101 can: acquire procurement demand information and a procurement item knowledge graph; perform entity extraction on the procurement demand information to obtain procurement demand entities; query attribute entities of a plurality of items from the procurement item knowledge graph; and match the procurement demand entities and the attribute entities of the plurality of items to obtain a target item list corresponding to the procurement demand information.

[0038] It should be understood that Figure 1 the number of terminal devices, networks, and servers in

[0039] In the following, each step of the information processing method in the example embodiments of the present disclosure will be described in more detail in conjunction with the accompanying drawings and embodiments.

[0040] Figure 2 is a flowchart of an information processing method according to an exemplary embodiment. The method provided by the embodiments of the present disclosure can be executed in the server 101 as Figure 1 shown, but the present disclosure is not limited thereto.

[0041] As Figure 2 shown, the information processing method provided by the embodiments of the present disclosure can include the following steps.

[0042] In step S202, procurement demand information and a procurement item knowledge graph are acquired.

[0043] In the embodiments of the present disclosure, the procurement demand information can be information related to procurement demand proposed by procurement personnel of an enterprise in a procurement process, and the procurement demand information can include but is not limited to an article name, a specification requirement, a purchase quantity, a use, a supplier requirement, and other requirements.

[0044] Figure 3 is a schematic diagram of procurement demand information and extraction of procurement demand information as entities according to an example.

[0045] Reference Figure 3 For example, the procurement demand information 301 includes a purchase article, a specification requirement, a purchase quantity, a use, a supplier requirement, and other requirements, wherein the purchase article is "a certain brand of variable frequency air conditioner", the specification requirement is "material: stainless steel; working voltage: 220V; unlocking method: fingerprint unlocking; fingerprint capacity: 20; standby power consumption: 30uA; weight: 140g±2g; working temperature: -10℃-+60℃; storage temperature: -10℃-+6℃; number of matches: 3P", the purchase quantity is 80, the use is a conference room, the supplier requirement is "no supply risk and no business risk", and the other requirements are "preferably a well-known brand and a market hot-selling article".

[0046] In the embodiments of the present disclosure, the procurement article knowledge graph can be constructed in advance according to article data, supplier data, and network public opinion data, and can include attribute entities of various procurement articles.

[0047] In the embodiments of the present disclosure, the procurement personnel of the enterprise can input a batch of procurement demand information, and the server can analyze the procurement demand information, wherein the analysis of the procurement demand information can include entity extraction and compensation of the procurement demand information.

[0048] In step S204, the procurement demand information is subjected to entity extraction to obtain procurement demand entities.

[0049] In the embodiments of the present disclosure, the procurement demand entity is an entity noun used to represent procurement demand, for example, the procurement demand entity can include air conditioner, stainless steel, 140g, and the like.

[0050] In the embodiments of the present disclosure, the entity extraction of the procurement demand information can obtain one or more procurement demand entities.

[0051] For example, continuing to refer to Figure 3 The entity extraction of the procurement demand information 301 can obtain procurement demand entities 302 (also referred to as a procurement demand entity sequence), which include air conditioner, material, stainless steel, working voltage, 220, unlocking method, fingerprint unlocking, fingerprint capacity, 20, weight, 140g, number of matches, 3, no risk, and hot-selling.

[0052] In an example embodiment, the entity extraction on the procurement demand information to obtain the procurement demand entity can include: labeling the procurement demand information by a sequence labeling model to obtain a label sequence of the procurement demand information; and extracting the procurement demand entity from the procurement demand information according to the labels in the label sequence.

[0053] In the embodiments of the present disclosure, each element in the procurement demand information can be labeled by a sequence labeling model to obtain a label sequence of the procurement demand information; and the procurement demand entity can be extracted from the procurement demand information according to the meanings of the labels in the label sequence.

[0054] For example, the procurement demand information is “a certain brand of variable frequency air conditioner”, each element in the procurement demand information is labeled by a sequence labeling model, and the label sequence is “BIEBEBE”. Each label has a corresponding meaning, for example, B represents the first character of the element as an entity, I represents the middle character of the element as an entity, and E represents the tail character of the element as an entity. According to the label sequence, the entities “a certain brand”, “variable frequency” and “air conditioner” can be extracted from the procurement demand information “a certain brand of variable frequency air conditioner”.

[0055] In an example embodiment, the method can further include: obtaining user behavior data of the purchaser; analyzing the user behavior data by a context relationship to obtain procurement background information of the purchaser; and compensating the procurement demand entity according to the procurement background information to update the procurement demand entity.

[0056] In the embodiments of the present disclosure, the user behavior data of the purchaser can include, but is not limited to, search data, delivery data, click data, collection data, and shopping cart data, and the procurement background information can be information for representing potential demand of the purchaser.

[0057] It should be noted that the personal information data involved in the embodiments of the present disclosure has been voluntarily authorized by the user, and the acquisition, storage, processing and transmission of personal information meet the requirements of relevant laws and regulations and public order and good customs.

[0058] In the embodiments of the present disclosure, a compensation mechanism can be used, that is, the user behavior data is analyzed by a context relationship to obtain procurement background information of the purchaser, and then the procurement background information can be directly used as a new procurement demand entity, or the procurement background information is extracted as a new procurement demand entity after entity extraction to be added to the sequence of procurement demand entities. Specifically, the potential motivation of the procurement demand of the purchaser can be compensated based on the user behavior data (search, delivery address, click, collection, and shopping cart).

[0059] For example, the purchase demand information of the purchaser includes "buy a certain air conditioner", entity extraction is performed on the purchase demand information, and the purchase demand entity "air conditioner" and "certain" are obtained. Then, it can be obtained that the surface demand of the purchaser is to buy an air conditioner and the brand is certain. The user behavior data of the purchaser includes searching "office decoration", and the context relationship analysis can obtain that the purchaser is likely to do office decoration. The user behavior data of the purchaser includes searching "common delivery location: Tibet", and the context relationship analysis can obtain that the potential demand of the purchaser is highland and high altitude. The "office decoration", "highland" and "high altitude" obtained by analysis can be used as new purchase demand entities.

[0060] In the embodiment of the present disclosure, the above compensation mechanism can comprehensively analyze and supplement the purchase demand of the purchaser, and obtain a more comprehensive portrait of the purchase demand of the purchaser.

[0061] In step S206, the attribute entities of a plurality of items are obtained by querying the purchase item knowledge graph.

[0062] In the embodiment of the present disclosure, the purchase item knowledge graph can include attribute entities of a plurality of items, relationships between the attribute entities, and relationships between the attribute entities and other entities (such as suppliers, purchasers, public opinion entities, etc.). The attribute entity of an item is used to describe the attribute information of the purchase item, which can include item name, model, specification parameter, brand information, etc.

[0063] In the embodiment of the present disclosure, the attribute entities of each item can be obtained by querying the pre-constructed purchase item knowledge graph.

[0064] Specifically, the graph query method can be used to query the entity and relationship data of items (such as goods), scenes, public opinions, suppliers, etc. in the purchase item knowledge graph.

[0065] Figure 4 FIG. 1 is a schematic diagram of matching a purchase demand entity and an attribute entity of a commodity according to an example.

[0066] For example, referring to FIG. 1, Figure 4 The purchase demand information analysis module 401 can analyze the purchase demand information proposed by the purchaser, obtain the entity name sequence of the commodity demand (including a plurality of purchase demand entities), and also obtain the entity name sequence of the scene demand, the entity name sequence of the public opinion, the entity name sequence of the user behavior, and the entity name sequence of the supplier preference. The attribute entity of the commodity can be obtained from the purchase item knowledge graph 402, and the scene entity relationship of the commodity, the public opinion entity relationship of the commodity, the user entity relationship of the commodity, and the supplier entity relationship of the commodity can also be obtained.

[0067] In the embodiments of the present disclosure, based on the knowledge data of the procurement item knowledge graph, the alignment of the procurement demand entity noun sequence (also referred to as procurement demand portrait) to the entity noun in the procurement item knowledge graph can be realized through a graph alignment model, so as to facilitate the subsequent matching of the procurement demand entity and the attribute entity of the plurality of items.

[0068] In step S208, the procurement demand entity and the attribute entity of the plurality of items are matched to obtain a target item list corresponding to the procurement demand information.

[0069] In the embodiments of the present disclosure, the procurement demand entity and the attribute entity of the item can be matched through the text similarity of each procurement demand entity and each attribute entity of the item, and the target item list corresponding to the procurement demand information can be determined according to the number of matches, wherein the number of target items included in the target item list can be set according to the demand, and the present disclosure does not limit this.

[0070] In the exemplary embodiments, matching the procurement demand entity and the attribute entity of the plurality of items to obtain a target item list corresponding to the procurement demand information can include: determining the text similarity of the procurement demand entity and the attribute entity of the plurality of items; determining the target attribute entity matched with the procurement demand entity from the attribute entity according to the text similarity; and determining at least one target item according to the target attribute entity to compose the target item list.

[0071] In the embodiments of the present disclosure, the text similarity of the procurement demand entity and the attribute entity of the plurality of items can be determined through NLP (Natural Language Processing), for example, the word2vec word vector training method can be used to judge whether two entities are the same or similar.

[0072] The word2vec is a group of related models used to generate word vectors. These models are shallow and two-layer neural networks used to train to restructure linguistic word texts, which can convert words into vector form, and can simplify the processing of text content into vector operations in a vector space, and calculate the similarity in the vector space to represent the similarity in the text semantics. The word2vec provides an effective continuous bag-of-words and skip-gram architecture implementation for calculating vector words.

[0073] In the embodiments of the present disclosure, after the text similarity of the procurement demand entity and the attribute entity of each item is calculated, the attribute entity with a text similarity greater than a similarity threshold can be determined as a target attribute entity matched with the procurement demand entity, and then the item corresponding to the target attribute entity is determined as a target item, the target items are combined into a target item list for recommendation to the purchaser.

[0074] For example, referring to Figure 4 , after calculating the similarity by NLP semantic comparison, it is determined that the procurement demand entity "EXTRA volume" and the attribute entity "EXTRA volume" of the commodity are similar, the procurement demand entity "color" and the attribute entity "color" of the commodity are similar, and the procurement demand entity "black" and the attribute entity "black" of the commodity are similar, then the commodity corresponding to the attribute entities "EXTRA volume", "color" and "black" can be determined as target commodities, and the target commodities can also be determined according to the number of matched entities, for example, the top 50 commodities with the most matched entities can be determined as target commodities.

[0075] In the exemplary embodiments, determining at least one target item according to the target attribute entity to combine into a target item list can include: determining the matching degree of each target item and the procurement demand information; obtaining the price attribute information and the public opinion attribute information of each target item; and determining a target push item from the at least one target item according to the matching degree of each target item and the procurement demand information, the price attribute information and the public opinion attribute information, to combine into a target item list.

[0076] In the embodiments of the present disclosure, after the target items are determined, each target item can be scored according to the matching degree of each target item and the procurement demand information, the price attribute information and the public opinion attribute information, and a target push item is selected from the target items according to the score of each target item to combine into a target item list for pushing to the purchaser.

[0077] Specifically, the target items (for example, the top 50 target items) are obtained according to the above steps, and the target items are sorted and scored, and three sets of models can be used in the sorting and scoring: a demand matching degree scoring model, a price scoring model and a risk scoring model.

[0078] Figure 5 is a schematic diagram of a demand matching degree scoring model according to an example.

[0079] For example, referring to Figure 5The demand matching degree scoring model mainly considers the matching relationship between the procurement demand and the target item, and scores each target item according to the matching relationship between the procurement demand and the target item. The score can be calculated by scoring the similarity between the procurement demand and the target item. For example, the text information of the procurement demand and each matched target item can be extracted, and the nouns are extracted according to the part-of-speech algorithm. Then, all the nouns of the procurement demand and the target item are converted into word vectors. The word vector is used to map the words in natural language to a fixed-dimensional space vector, realizing the standardization and quantization of natural language. For example, the word2vec word vector can be used for text similarity analysis. By using the mathematical quantization of the word vector, the nouns of the procurement demand and the target item are compared two by two. If the two nouns are the same, the score is 1. If they are not the same, the score between 0 and 1 can be calculated according to the spatial distance of the word vector. Finally, the average score of all the nouns is calculated as the matching degree score of the procurement demand and each target item. Similarly, the similarity score of the procurement demand and each target item is calculated.

[0080] For example, the demand matching degree scores of the procurement demand A and the target goods B, C and D are shown in Table 1. The nouns a1, a2 and a3 are extracted from the procurement demand A, the nouns b1, b2 and b3 are extracted from the target goods B, the nouns c1, c2 and c3 are extracted from the target goods C, and the nouns d1, d2 and d3 are extracted from the target goods D. The similarity scores between each noun of the procurement demand (i.e. a1, a2 and a3) and each noun of the target goods (e.g. the nouns of the target goods B are b1, b2 and b3) are calculated, for example, the similarity score of a1 and b1 is 1, the similarity score of a2 and b2 is 1, and the similarity score of a3 and b3 is 1. Then, the average score of the similarity scores of the nouns is taken as the demand matching degree score of the target goods.

[0081] Table 1

[0082]

[0083] The price scoring model can calculate the average price of the target goods, score the deviation of the price of each target good from the average price, and score the price of each target good by scoring the deviation of the price of each target good from the average price. The price of each target good is scored by scoring the deviation of the price of each target good from the average price.

[0084] The risk scoring model mainly considers public opinion risk, which can be divided into positive information and negative information. For example, a negative public opinion information is scored -1, and a positive public opinion information is scored 1.

[0085] After scoring by the demand matching degree scoring model, the price scoring model and the risk scoring model respectively, the scores obtained by the above three models can be added and averaged to obtain a comprehensive score, and the target push items (for example, 10 target items with higher comprehensive scores) are determined according to the comprehensive score to form a target item list to be pushed to the purchaser.

[0086] The information processing method provided in the embodiments of the present disclosure determines target push items from at least one target item according to the matching degree of each target item and the procurement demand information, the price attribute information and the public opinion attribute information, to form a target item list, which realizes re-optimization of the recommendation result, so that the recommended items are more accurate.

[0087] In the exemplary embodiments, the method can further include obtaining selected items selected by the purchaser from the target item list; and constructing a triple relationship according to the selected items and the procurement demand entity and storing the triple relationship into the procurement item knowledge graph.

[0088] In the embodiments of the present disclosure, the selected items can be items selected by the purchaser from the target item list for purchase, detail browsing or adding to a shopping cart.

[0089] In the embodiments of the present disclosure, after the selected items are determined, a relationship between the selected items and the procurement demand entity can be established and stored in the procurement item knowledge graph.

[0090] Specifically, the result of each selection of the purchaser can be stored in the knowledge graph as a relationship, for example, in the scenario of procurement demand for repairing a printer, the purchaser selects three goods (good A, good B and good C), and the three goods and the scenario of repairing a printer can be stored in the knowledge graph data as new entities and relationships (in the form of triples), and the new triple data can be:

[0091]

repair

printer

good A

[0092]

repair

printer

good B

[0093]

repair

printer

good C

[0094] Before storage, the triples can be annotated and edited by a human.

[0095] In the embodiments of the present disclosure, the triple relationship constructed according to the selected items selected by the purchaser from the target item list and the procurement demand entity and stored in the procurement item knowledge graph can be used as one of the recommendation bases for the next selection, so as to realize the accumulation of the selection experience and provide a basis for subsequent selection, so that the selection is more and more accurate.

[0096] The information processing method provided by the embodiments of the present disclosure can extract entities from the procurement demand information to obtain procurement demand entities, query attribute entities of a plurality of items from the procurement item knowledge graph, and automatically and accurately obtain a target item list corresponding to the procurement demand information by matching the procurement demand entities and the attribute entities of the items, thereby improving the accuracy of matching the procurement demand and the target items and improving the procurement efficiency. In addition, the method can save the workload of manual query, search and matching, save the operation steps and procurement time of the procurement party, and thus improve the user experience.

[0097] Figure 6 is a flowchart of another information processing method according to an exemplary embodiment. As shown in Figure 6 The difference between the above embodiment and the method provided by the embodiments of the present disclosure is that the method provided by the embodiments of the present disclosure can further include the following steps.

[0098] In step S602, original data is obtained, and the original data includes item data, supplier data and network public opinion data.

[0099] In the embodiments of the present disclosure, original data can be obtained to construct a procurement item knowledge graph, wherein the original data can include but is not limited to item data (such as commodity data), supplier data and network public opinion data, and the above data can be collected through an Internet channel.

[0100] Figure 7 is a schematic diagram of constructing a procurement item knowledge graph according to an example.

[0101] For example, referring to Figure 7 , the original data can include commodity data, supplier data, order data and Internet public opinion data, wherein the commodity data can include commodity title, attribute, details, etc., the supplier data can include supplier nouns, qualifications, etc., the order data can include purchaser, amount, quantity, purpose, etc., and the Internet public opinion data can include network hot comments, business credit, network negative, news keywords, etc.

[0102] In step S604, entity extraction is performed on the item data, the supplier data and the network public opinion data respectively to obtain item attribute entities, supplier attribute entities and network public opinion entities.

[0103] The supplier attribute entity is a noun used to represent the attributes of the supplier, for example: a certain scientific and technological company; and the network public opinion entity is a noun used to represent the network public opinion related information of the item, for example: a hot-selling, photo-taking device.

[0104] ​In the embodiments of the present disclosure, the purchasing knowledge system relied on by the selected product can be built through the entity extraction technology of the knowledge graph. Specifically, the category, commodity, attribute, brand, evaluation, price and other data nouns are extracted from the item data through the entity extraction technology of the knowledge graph to form the item attribute entity of the purchasing item knowledge graph. The entity nouns are extracted from the supplier data and network public opinion data using the same method to obtain the supplier attribute entity and network public opinion entity.

[0105] When extracting the network public opinion data, the corresponding public opinion keywords can be obtained by accessing the enterprise credit data interface of the three-party credit investigation company and the Internet public opinion collection related keywords, and the keywords are stored in the form of labels.

[0106] In the embodiments of the present disclosure, the entity extraction can be performed by the regular and semantic model, but the present disclosure is not limited thereto.

[0107] In step S606, the purchasing item knowledge graph is constructed according to the item attribute entity, the supplier attribute entity and the network public opinion entity.

[0108] In the embodiments of the present disclosure, the relationship between the item attribute entity, the supplier attribute entity and the network public opinion entity can be mined through the relationship of the item data, order data and the like, and the knowledge graph triplets are constructed and stored, wherein the triplet is the basic unit of knowledge representation in the knowledge graph, and the triplet can be used to represent the relationship between entities or the attribute value of an entity. From the content, the structure of the triplet can be "resource-attribute-attribute value".

[0109] For example, referring to Figure 7 The above product nouns, attribute nouns and attribute values can be manually annotated and edited to be stored in the form of knowledge graph triplets, and the triplets can include, for example: Xue Yao v5-brand-Xue, Xue Yao v5-model-v5, Xue Yao v5-memory-256G, Xue Yao v5-camera-50 million, Xue Yao v5-supplier-some scientific and technological company, Xue Yao v5-scene-office, Xue Yao v5-public opinion label-photographing tool.

[0110] The information processing method provided by the embodiments of the present disclosure constructs the purchasing item knowledge graph with the purchasing item as the core from multiple dimensions based on the item data, the supplier data and the network public opinion data, provides a knowledge type data query basis for the subsequent purchasing process, and thus improves the purchasing efficiency.

[0111] Figure 8 is a schematic diagram of an information processing system according to an example.

[0112] Referring to Figure 8 , the system can include a knowledge graph construction module 801, a procurement demand analysis module 802, a commodity recommendation engine module 803, a commodity recommendation degree scoring module 804, and a product selection experience sedimentation module 805. Among them, the knowledge graph construction module 801 is used to extract commodity data, supplier data, historical transaction data and external public opinion data to construct a knowledge graph; the procurement demand analysis module 802 is used to receive batch procurement demand, analyze the procurement demand, which can specifically include extracting entities from the procurement demand and compensating the procurement demand using a compensation mechanism; the commodity recommendation engine module 803 is used to find the most suitable matching commodity from the knowledge graph using the entity alignment method, and remove the commodities that do not meet the requirements; the commodity recommendation degree scoring module 804 is used to score the commodities using a demand matching degree scoring model, a price scoring model and a risk scoring model to obtain batch product selection results; the product selection experience sedimentation module 805 is used for experience sedimentation and data backflow, that is, new triple relationship can be constructed according to the commodities selected by the procurement party, and artificial annotation is performed to edit the knowledge graph.

[0113] It should be noted that the above-described figures are only schematic representations of the processes included in the method according to the exemplary embodiments of the present disclosure, and are not for limiting purposes. It is easy to understand that the processes shown in the above-described figures do not indicate or limit the time sequence of these processes. In addition, it is also easy to understand that these processes can be executed synchronously or asynchronously, for example, in multiple modules.

[0114] The following is a device embodiment of the present disclosure, which can be used to execute the method embodiments of the present disclosure. For details not disclosed in the device embodiments of the present disclosure, please refer to the method embodiments of the present disclosure.

[0115] Figure 9 is a block diagram of an information processing device according to an exemplary embodiment.

[0116] As Figure 9 shown, the information processing device 900 can include an acquisition module 902, an obtaining module 904, a query module 906, and a matching module 908.

[0117] Among them, the acquisition module 902 is used to acquire procurement demand information and procurement item knowledge graph; the obtaining module 904 is used to perform entity extraction on the procurement demand information to obtain procurement demand entities; the query module 906 is used to query attribute entities of a plurality of items from the procurement item knowledge graph; the matching module 908 is used to match the procurement demand entities and the attribute entities of the plurality of items to obtain a target item list corresponding to the procurement demand information.

[0118] In some example embodiments of the present disclosure, the obtaining module 904 is further configured to label the procurement demand information by a sequence labeling model to obtain a label sequence of the procurement demand information, and extract the procurement demand entity from the procurement demand information according to a label in the label sequence.

[0119] In some example embodiments of the present disclosure, the apparatus 900 further comprises a data obtaining module configured to obtain user behavior data of a procurement party, an information obtaining module configured to obtain procurement background information of the procurement party by analyzing the user behavior data according to a context relationship, and a compensation module configured to compensate the procurement demand entity according to the procurement background information to update the procurement demand entity.

[0120] In some example embodiments of the present disclosure, the matching module 908 is further configured to determine a text similarity between the procurement demand entity and attribute entities of the plurality of items, determine a target attribute entity matched with the procurement demand entity from the attribute entities according to the text similarity, and determine at least one target item according to the target attribute entity to compose the target item list.

[0121] In some example embodiments of the present disclosure, the matching module 908 is further configured to determine a matching degree between each target item and the procurement demand information, obtain price attribute information and public opinion attribute information of each target item, and determine a target push item from the at least one target item according to the matching degree between each target item and the procurement demand information, the price attribute information and the public opinion attribute information to compose the target item list.

[0122] In some example embodiments of the present disclosure, the apparatus 900 further comprises a data obtaining module configured to obtain original data, the original data comprising item data, supplier data and network public opinion data, an entity extraction module configured to extract entities from the item data, the supplier data and the network public opinion data respectively to obtain item attribute entities, supplier attribute entities and network public opinion entities, and a graph construction module configured to construct the procurement item knowledge graph according to the item attribute entities, the supplier attribute entities and the network public opinion entities.

[0123] In some example embodiments of the present disclosure, the apparatus 900 further comprises an item obtaining module configured to obtain a selected item from the target item list by a procurement party, and a relationship construction module configured to construct a triple relationship according to the selected item and the procurement demand entity and store the triple relationship to the procurement item knowledge graph.

[0124] It is to be noted that the block diagrams shown in the above-described drawings are functional entities, and do not necessarily have to correspond to physically or logically independent entities. These functional entities can be implemented in software, or in one or a plurality of hardware modules or integrated circuits, or in different network and / or processor devices and / or microcontroller devices.

[0125] Figure 10 is a structural diagram of an electronic device according to an exemplary embodiment. It is to be noted that Figure 10 The electronic device shown is merely an example, and should not impose any limitation on the functions and usage range of the embodiments of the present disclosure.

[0126] As Figure 10 shown, the electronic device 1000 includes a central processing unit (CPU) 1001, which can perform various appropriate actions and processes in accordance with a program stored in a read only memory (ROM) 1002 or a program loaded from a storage section 1008 into a random access memory (RAM) 1003. Various programs and data required for the operation of the system 1000 are also stored in the RAM 1003. The CPU 1001, the ROM 1002, and the RAM 1003 are connected to each other through a bus 1004. An input / output (I / O) interface 1005 is also connected to the bus 1004.

[0127] The following components are connected to the I / O interface 1005: an input section 1006 including a keyboard, a mouse, etc.; an output section 1007 including a display such as a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 1008 including a hard disk, etc.; and a communication section 1009 including a network interface card such as a LAN card, a modem, etc. The communication section 1009 performs communication processing via a network such as the Internet. A drive 1010 is also connected to the I / O interface 1005 as necessary. A removable recording medium 1011 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc. is attached to the drive 1010 as necessary, so that a computer program read out therefrom is installed in the storage section 1008 as necessary.

[0128] In particular, the processes described above with reference to the flowcharts can be implemented as a computer software program in accordance with embodiments of the present disclosure. For example, embodiments of the present disclosure include a computer program product comprising a computer program carried on a computer readable medium, the computer program comprising program code for executing the methods illustrated by the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network by the communication section 1009, and / or installed from the detachable medium 1011. When the computer program is executed by the central processing unit (CPU) 1001, the above-described functions defined in the system of the present disclosure are executed.

[0129] It should be noted that the computer readable medium shown in the present disclosure can be a computer readable signal medium or a computer readable storage medium or any combination of the two. The computer readable storage medium may, for example, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or apparatus, or any combination of the above. More specific examples of the computer readable storage medium can include, but are not limited to, an electrical connection having one or more wires, a portable computer diskette, 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 above. In the present disclosure, the computer readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, device or apparatus. In the present disclosure, the computer readable signal medium can include a data signal carried in a baseband or as a part of a carrier wave, which carries computer readable program code. Such a propagated data signal can take many forms, including but not limited to, an electromagnetic signal, an optical signal or any suitable combination of the above. The computer readable signal medium can also be any computer readable medium that can send, propagate or transfer a program for use by or in connection with an instruction execution system, device or apparatus. The program code contained on the computer readable medium can be transmitted by any suitable medium, including but not limited to wireless, wire, optical cable, RF or the like, or any suitable combination of the above.

[0130] The flow and block diagrams in the drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flow and block diagrams can represent a module, a segment, or a portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that in some alternative implementations, the functions noted in the blocks can occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently or the blocks can sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and / or flowchart illustrations, and combinations thereof, can be implemented by special purpose hardware-based systems that perform the specified functions or operations, or combinations of special purpose hardware and computer instructions.

[0131] The units described in the embodiments of the present disclosure can be implemented by software, or by hardware. The units described can be arranged in a processor, for example, can be described as: a processor includes a sending unit, an obtaining unit, a determining unit and a first processing unit. In some cases, the names of these units do not constitute a limitation on the units themselves, for example, the sending unit can also be described as: a unit for sending a picture obtaining request to a connected server.

[0132] As another aspect, the present disclosure also provides a computer-readable storage medium, which can be included in the electronic device described in the above embodiments, or can exist separately without being assembled into the electronic device. The computer-readable storage medium carries one or more programs, which, when executed by the electronic device, cause the electronic device to implement the method described in the above embodiments. For example, the electronic device can implement the steps shown in the above embodiments. Figure 2

[0133] According to an aspect of the present disclosure, a computer program product or computer program is provided, which includes computer instructions stored in a computer readable storage medium. A processor of a computer device reads the computer instructions from the computer readable storage medium, and the processor executes the computer instructions, so that the computer device executes the method provided in various optional implementations of the above embodiments.

[0134] It should be understood that the number of any elements in the drawings of the present disclosure is used for example and not limitation, and any naming is only for distinction and does not have any limiting meaning.

[0135] ​Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the features disclosed herein. It is intended that the disclosure be construed as including any paterns of this disclosure that can be derived from the description and illustrations presented herein without departing from the scope and spirit of the disclosure. The specification and examples given are considered exemplary only, and the true scope and spirit of the disclosure are indicated by the following claims.

[0136] It is to be understood that the disclosure is not limited to the precise construction described above and shown in the attached drawings, and that various modifications and changes can be made without departing from the scope thereof. The scope of the disclosure is limited only by the claims that follow.

Claims

1. An information processing method, characterized in that, include: Obtain procurement demand information and a knowledge graph of the items to be procured; Entity extraction is performed on the procurement demand information to obtain the procurement demand entity; Multiple item attribute entities are obtained by querying the knowledge graph of the purchased items; The procurement demand entity and the attribute entities of the multiple items are matched to obtain a list of target items corresponding to the procurement demand information; The method further includes: Acquire user behavior data from the purchasing party, wherein the user behavior data from the purchasing party includes search data, delivery data, click data, favorites data, and added-to-cart data; By analyzing the user behavior data through contextual relationships, the procurement background information of the purchaser is obtained, and the procurement background information is used to characterize the potential needs of the purchaser. The procurement demand entity is compensated based on the procurement background information to update the procurement demand entity. Specifically, this includes: using the procurement background information as a new procurement demand entity, or extracting entities from the procurement background information and using them as a new procurement demand entity to add to the procurement demand entity sequence; and compensating the potential motivation of the procurement party's procurement demand based on the user behavior data.

2. The method according to claim 1, characterized in that, Entity extraction is performed on the aforementioned procurement demand information to obtain procurement demand entities, including: The procurement requirement information is labeled using a sequence labeling model to obtain a label sequence for the procurement requirement information; The procurement demand entity is obtained from the procurement demand information based on the tags in the tag sequence.

3. The method according to claim 1, characterized in that, Matching the procurement demand entity and the attribute entities of the multiple items to obtain a list of target items corresponding to the procurement demand information, including: Determine the text similarity between the procurement demand entity and the attribute entities of the multiple items; Based on the text similarity, a target attribute entity that matches the procurement demand entity is determined from the attribute entities; At least one target item is determined based on the target attribute entity to form the target item list.

4. The method according to claim 3, characterized in that, Based on the target attribute entity, at least one target item is determined to form the target item list, including: Determine the matching degree between each target item and the procurement requirement information; Obtain price and public opinion information for each target item; Based on the matching degree between each target item and the procurement demand information, price attribute information, and public opinion attribute information, target push items are determined from the at least one target item to form the target item list.

5. The method according to claim 1, characterized in that, Also includes: Acquire raw data, which includes product data, supplier data, and online public opinion data; Entity extraction is performed on the item data, the supplier data, and the online public opinion data to obtain item attribute entities, supplier attribute entities, and online public opinion entities; The knowledge graph of the procured items is constructed based on the item attribute entity, the supplier attribute entity, and the online public opinion entity.

6. The method according to claim 5, characterized in that, Also includes: Obtain the selected items chosen by the purchaser from the target item list; A triplet relationship is constructed based on the selected item and the procurement demand entity, and stored in the procurement item knowledge graph.

7. An information processing device, characterized in that, include: The acquisition module is used to acquire procurement demand information and a knowledge graph of the items to be procured. The acquisition module is used to extract entities from the procurement demand information to obtain the procurement demand entities. The process involves acquiring user behavior data from the purchasing party, including search data, delivery data, click data, favorites data, and added-to-cart data; analyzing the user behavior data through contextual relationships to obtain the purchasing party's purchasing background information, which characterizes the purchasing party's potential needs; and compensating for the purchasing demand entity based on the purchasing background information to update the purchasing demand entity. Specifically, this includes either using the purchasing background information as a new purchasing demand entity, or extracting entities from the purchasing background information and using it as a new purchasing demand entity to add to the purchasing demand entity sequence, thereby compensating for the purchasing party's potential motivations for purchasing needs based on the user behavior data. The query module is used to query and obtain the attribute entities of multiple items from the knowledge graph of the purchased items; The matching module is used to match the procurement demand entity and the attribute entities of the multiple items to obtain a list of target items corresponding to the procurement demand information.

8. An electronic device, characterized in that, include: At least one processor; A storage device for storing at least one program, which, when executed by the at least one processor, causes the at least one processor to implement the information processing method as described in any one of claims 1 to 6.

9. A computer-readable storage medium having computer-executable instructions stored thereon, characterized in that, When the executable instructions are executed by the processor, they implement the information processing method as described in any one of claims 1 to 6.

Images