WO2020077876A1 - 企业供销关系图谱生成方法、装置和计算机设备 - Google Patents

企业供销关系图谱生成方法、装置和计算机设备 Download PDF

Info

Publication number
WO2020077876A1
WO2020077876A1 PCT/CN2018/125457 CN2018125457W WO2020077876A1 WO 2020077876 A1 WO2020077876 A1 WO 2020077876A1 CN 2018125457 W CN2018125457 W CN 2018125457W WO 2020077876 A1 WO2020077876 A1 WO 2020077876A1
Authority
WO
WIPO (PCT)
Prior art keywords
enterprise
target
queried
information
supply
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/CN2018/125457
Other languages
English (en)
French (fr)
Inventor
陈旷雨
杨亮吉
赵坤
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
OneConnect Smart Technology Co Ltd
Original Assignee
OneConnect Smart Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by OneConnect Smart Technology Co Ltd filed Critical OneConnect Smart Technology Co Ltd
Publication of WO2020077876A1 publication Critical patent/WO2020077876A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/901—Indexing; Data structures therefor; Storage structures

Definitions

  • the present application relates to a method, device and computer equipment for generating an enterprise supply and marketing relationship graph.
  • the server often can only calculate and analyze the data of a layer of upstream and downstream relations of an enterprise, and obtain a single enterprise supply and marketing relationship atlas.
  • the inventor realized that the traditional enterprise supply and marketing relationship atlas obtained by the traditional method is difficult to cover the whole picture of the actual supply and marketing system of the enterprise, resulting in the inability to truly understand the actual supply and marketing relationship of the enterprise, resulting in low accuracy of the acquired enterprise supply and marketing relationship.
  • a method, an apparatus, and a computer device for generating an enterprise supply and marketing relationship graph are provided.
  • a method for generating an enterprise supply and marketing relationship graph includes:
  • the query request carrying identification information of the enterprise to be queried
  • a supply and marketing relationship map of the enterprise corresponding to the enterprise to be queried is generated according to the enterprise to be queried and the target enterprise at each layer obtained.
  • An apparatus for generating a supply-sale relationship graph of an enterprise includes:
  • the request receiving module is used to receive the query request sent by the terminal, where the query request carries identification information of the enterprise to be queried;
  • the information query module is used to query the database according to the identification information of the enterprise to be queried to obtain invoice information corresponding to the enterprise to be queried;
  • a first information extraction module configured to extract the information of the target enterprise from the invoice information corresponding to the enterprise to be queried
  • a second information extraction module used to obtain the invoice information of the target enterprise, and extract the information of the target enterprise again from the invoice information of the target enterprise; until the number of layers of the extracted target enterprise meets the set conditions;
  • the map generation module is used to generate a supply and marketing relationship map of the enterprise corresponding to the enterprise to be queried according to the enterprise to be queried and the obtained target enterprise of each layer when the extracted number of target enterprises meets the set conditions.
  • a computer device includes a memory and one or more processors.
  • the memory stores computer-readable instructions.
  • the one or more processors are executed The following steps:
  • the query request carrying identification information of the enterprise to be queried
  • a supply and marketing relationship map of the enterprise corresponding to the enterprise to be queried is generated according to the enterprise to be queried and the target enterprise at each layer obtained.
  • the processor also implements the following steps when executing the computer-readable instructions: acquiring the preset invoice information template; acquiring the position label of the target enterprise's information in the preset invoice information template; In the invoice information, determine the location to be extracted corresponding to the location label; and extract the information of the target company of the location to be extracted.
  • the processor executes the computer-readable instructions, the following steps are further implemented: the enterprise to be queried is regarded as the base-level target enterprise; the base-level target enterprise and the obtained target-level enterprise are arranged in the first order, after the arrangement Target companies; according to the ranked target companies, obtain the supply and marketing relationship between the target companies in the adjacent layer; and according to the supply and marketing relationship between the aligned target companies and the target companies in the adjacent layer, generate a correspondence with the enterprises to be queried Of the enterprise's supply and marketing relationship.
  • the processor also implements the following steps when executing the computer-readable instructions: after generating the enterprise supply and marketing relationship map corresponding to the enterprise to be queried, each target enterprise is divided into different initial enterprise communities, and Obtain the module degree corresponding to each initial enterprise community; the module degree is generated according to the virtual structure corresponding to the enterprise community; divide the target enterprise into the initial enterprise community adjacent to the target enterprise to obtain the intermediate enterprise community; obtain the intermediate The modularity of the corporate community, if the modularity is greater than that of the initial corporate community, this division will be accepted; the target enterprise will be divided again into the intermediate corporate community adjacent to the target enterprise until the The module degree reaches the corresponding threshold; and when the obtained module degree of the enterprise community reaches the corresponding threshold, the obtained enterprise community is obtained as the target enterprise community.
  • the processor also implements the following steps when executing the computer-readable instructions: acquiring the target enterprise in the same target enterprise community; identifying the lower-level target enterprise of the target enterprise, and acquiring the initial importance value and target enterprise of the lower-level target enterprise The number of transactions with the lower-level target enterprise; according to the correspondence between the number of transactions and the weight, determine the weight corresponding to the acquired transaction number; based on the initial importance value of the lower-level target enterprise and the weight, the target important value of the lower-level target enterprise is obtained ; And obtain the sum of the target important values of each lower-level target company as the target company's important value, and determine the importance level corresponding to the target company's important value.
  • the processor also implements the following steps when executing computer-readable instructions: acquiring historical invoice information of the target enterprise within a preset time range; generating invoice verification files corresponding to the target enterprise based on the historical invoice information; The invoice verification document verifies the invoice information of the target enterprise; and if the invoice information verification is incorrect, a corresponding warning message is generated and sent to the corresponding target enterprise.
  • the processor also implements the following steps when executing the computer-readable instructions: extracting the target enterprise in the generated enterprise supply and marketing relationship atlas; obtaining basic information corresponding to each target enterprise; and integrating the enterprise supply and marketing relationship atlas and each The basic information of the target enterprise is loaded into the preset supply and marketing relationship report template in the second order to generate the supply and marketing relationship report of the enterprise to be queried.
  • One or more non-volatile computer-readable storage media storing computer-readable instructions.
  • the computer-readable instructions When executed by one or more processors, the one or more processors perform the following steps:
  • the query request carrying identification information of the enterprise to be queried
  • a supply and marketing relationship map of the enterprise corresponding to the enterprise to be queried is generated according to the enterprise to be queried and the target enterprise at each layer obtained.
  • the following steps are also achieved: obtaining a preset invoice information template; obtaining a position label of the target enterprise's information in the preset invoice information template; In the invoice information, determine the location to be extracted corresponding to the location label; and extract the information of the target company of the location to be extracted.
  • the enterprise to be queried is regarded as the base-level target enterprise; the base-level target enterprise and the obtained target-level enterprise are arranged in the first order to obtain the arrangement After the target enterprises, according to the arranged target enterprises, obtain the supply and marketing relationship between the target companies in the adjacent layer; and according to the supply and marketing relationship between the aligned target enterprises and the adjacent layer of target companies, generate and query enterprises Corresponding enterprise supply and marketing relationship atlas.
  • each target enterprise is divided into different initial enterprise communities, And obtain the module degree corresponding to each initial enterprise community; the module degree is generated according to the virtual structure corresponding to the enterprise community; the target enterprise is divided into the initial enterprise community adjacent to the target enterprise to obtain the intermediate enterprise community; obtain The modularity of the intermediate enterprise community, if the modularity is greater than the initial enterprise community, accept this division; divide the target enterprise into the intermediate enterprise community adjacent to the target enterprise again, until the obtained enterprise community The degree of modularity reaches the corresponding threshold; and when the degree of modularity of the obtained enterprise community reaches the corresponding threshold, the obtained enterprise community is obtained as the target enterprise community.
  • the following steps are also achieved: acquiring the target enterprise in the same target enterprise community; identifying the lower-level target enterprise of the target enterprise, and acquiring the initial important value and target of the lower-level target enterprise The number of transactions between the enterprise and the lower target enterprise; according to the correspondence between the number of transactions and the weight, the weight corresponding to the acquired transaction number is determined; based on the initial importance value and weight of the lower target enterprise, the target important value of the lower target enterprise is obtained; And obtain the sum of the target important values of each lower-level target company as the target company's important value, and determine the importance level corresponding to the target company's important value.
  • the following steps are also achieved: acquiring historical invoice information of the target enterprise within a preset time range; generating invoice verification files corresponding to the target enterprise based on the historical invoice information; According to the invoice verification document, verify the invoice information of the target enterprise; and if the invoice information verification is incorrect, generate a corresponding warning message and send the warning message to the corresponding target enterprise.
  • the computer-readable instructions are executed by the processor to implement the following steps: extract target enterprises in the generated enterprise supply and marketing relationship atlas; obtain basic information corresponding to each target enterprise; and convert the enterprise supply and marketing relationship atlas and The basic information of each target enterprise is loaded into the preset supply and marketing relationship report template in the second order to generate the supply and marketing relationship report of the enterprise to be queried.
  • FIG. 1 is an application scenario diagram of a method for generating an enterprise supply and marketing relationship graph according to one or more embodiments.
  • FIG. 2 is a schematic flowchart of a method for generating an enterprise supply and marketing relationship graph according to one or more embodiments.
  • FIG. 3 is a schematic flowchart of steps for extracting information of a target enterprise from invoice information corresponding to an enterprise to be queried according to one or more embodiments.
  • FIG. 4 is a schematic diagram of an enterprise supply and marketing relationship graph according to one or more embodiments.
  • FIG. 5 is a schematic flowchart of a method for generating an enterprise supply and marketing relationship graph in another embodiment.
  • FIG. 6 is a block diagram of a map generation system according to one or more embodiments.
  • FIG. 7 is a block diagram of an apparatus for generating a supply-sale relationship graph of an enterprise according to one or more embodiments.
  • FIG. 8 is a block diagram of a computer device in accordance with one or more embodiments.
  • the method for generating an enterprise supply and marketing relationship graph provided by this application can be applied to the application environment shown in FIG. 1.
  • the terminal 110 and the server 120 communicate through the network.
  • the terminal 110 is installed with a map generation system; the terminal 110 generates a query request by recognizing the user's input operation on the operation interface corresponding to the map generation system, and sends the query request to the server 120; the query request carries the user-entered logo of the company to be queried information.
  • the server 120 parses the query request to obtain the identification information of the enterprise to be queried; queries the database according to the identification information of the enterprise to be queried to obtain invoice information corresponding to the enterprise to be queried; and extracts the target enterprise information from the invoice information corresponding to the enterprise to be queried; Obtain the target company's invoice information, and extract the target company's information from the target company's invoice information again; until the extracted target company's layers meet the set conditions; when the extracted target company's layers meet the set conditions, According to the enterprise to be queried and the target enterprises at each layer obtained, a graph of the enterprise supply and marketing relationship corresponding to the enterprise to be queried is generated, and the generated graph of the enterprise supply and marketing relationship is sent to the terminal 110.
  • the terminal 110 may be, but not limited to, various personal computers, notebook computers, smart phones, and tablet computers.
  • the server 120 may be implemented by an independent server or a server cluster composed of multiple servers.
  • a method for generating an enterprise supply and sales relationship graph is provided.
  • the method is applied to the server in FIG. 1 as an example for illustration, including the following steps:
  • Step S201 Receive an inquiry request sent by the terminal, where the inquiry request carries identification information of the enterprise to be queried.
  • the identification information of the enterprise to be queried refers to the information used to identify the enterprise, which is convenient for the server to distinguish; for example, the name of the enterprise, the enterprise code, and the ID number of the person in charge of the enterprise.
  • the terminal is installed with a graph generation system.
  • the graph generation system can be used to generate an enterprise supply and marketing relationship atlas.
  • the terminal generates a corresponding query request by responding to the user's input operation on the operation interface corresponding to the graph generation system, and sends the query request to the server; the query request carries the identification information of the enterprise to be queried entered by the user.
  • the server receives the query request sent by the terminal, and obtains the identification information of the enterprise to be queried according to the query request.
  • Step S202 query the database according to the identification information of the enterprise to be queried to obtain invoice information corresponding to the enterprise to be queried.
  • the server obtains historical invoice information of different enterprises, and stores the historical invoice information according to the identification information of the enterprise into a pre-established database to facilitate subsequent search for invoice information corresponding to the enterprise to be queried.
  • the server parses the query request sent by the terminal to obtain the identification information of the enterprise to be queried; query the database according to the identification information of the enterprise to be queried, and obtain the invoice information whose identification information matches the identification information of the enterprise to be queried as the invoice information corresponding to the enterprise .
  • Step S203 Extract the information of the target enterprise from the invoice information corresponding to the enterprise to be queried.
  • the invoice information contains the information of the seller and the buyer.
  • the target enterprise refers to the buyer, and the position of the target enterprise in the invoice information is fixed.
  • the enterprise to be queried refers to the seller, and the target enterprise refers to the purchaser.
  • the server obtains the enterprise invoice information template, determines the position to be extracted from the invoice information of the enterprise to be queried according to the position of the target enterprise information in the enterprise invoice information template, and obtains the information of the target enterprise of the position to be extracted.
  • Obtaining the information of the target enterprise from the invoice information of the enterprise to be queried is beneficial to covering the target enterprise of the enterprise to be queried, avoiding the omission of the target enterprise, and further improving the accuracy of the obtained enterprise supply and marketing relationship.
  • Step S204 Obtain the invoice information of the target enterprise, and extract the information of the target enterprise again from the invoice information of the target enterprise; until the number of layers of the extracted target enterprise meets the set conditions.
  • the server obtains the invoice information of the target enterprise of the enterprise to be queried, extracts the information of the target enterprise again from the invoice information of the target enterprise, and so on, until the number of layers of the extracted target enterprise meets the set conditions;
  • the target enterprise is extracted from the invoice information for the purpose of obtaining the multi-layer supply and marketing relationship of the enterprise, avoiding the defect that the traditional method can only obtain the single-layer supply and marketing relationship of the enterprise, and further improving the accuracy of the obtained enterprise supply and marketing relationship.
  • Step S205 when the number of layers of the extracted target enterprise satisfies the set condition, the enterprise supply and marketing relationship map corresponding to the enterprise to be queried is generated according to the enterprise to be queried and the obtained target enterprise of each layer.
  • the server continuously extracts the target enterprise information from the invoice information of the enterprise, and counts the number of layers of the extracted target enterprise; when it is determined that the layer of the extracted target enterprise meets the set conditions, the server according to the enterprises to be Target companies at all levels generate the enterprise supply and marketing relationship atlas corresponding to the enterprise to be queried, which can cover the entire picture of the actual supply and marketing relationship of the enterprise to be queried, and further improve the accuracy of the acquired enterprise supply and marketing relationship.
  • the server receives the query request sent by the terminal, queries the database according to the identification information of the company to be queried carried in the query request, and obtains the invoice information corresponding to the company to be queried; from the invoice information corresponding to the company to be queried Extract the target company's information; obtain the target company's invoice information, and then extract the target company's information from the target company's invoice information; until the extracted target company's layers meet the set conditions; when the extracted target company's layer When the number satisfies the set conditions, according to the enterprises to be queried and the target enterprises of each layer obtained, the enterprise supply and marketing relationship map corresponding to the enterprises to be queried is generated; the target enterprises are continuously extracted from the invoice information of the enterprises to obtain multiple layers of enterprises
  • the purpose of the supply and marketing relationship avoids the defect that the traditional method can only obtain the single-layer supply and marketing relationship of the enterprise, guarantees a comprehensive understanding of the actual supply and marketing relationship of the enterprise, and avoids the o
  • the step of extracting the information of the target enterprise from the invoice information corresponding to the enterprise to be queried specifically includes:
  • Step S301 Acquire a preset invoice information template.
  • Step S302 Acquire a location label of the target enterprise's information in the preset invoice information template.
  • Step S303 Determine the location to be extracted corresponding to the location label from the invoice information corresponding to the enterprise to be queried.
  • Step S304 Extract the information of the target enterprise of the location to be extracted.
  • the server determines the position to be extracted corresponding to the position label in the invoice information by presetting the position label of the target enterprise information in the invoice information template, and obtains the information of the target enterprise of the position to be extracted, which is convenient for subsequent extraction of the information of the target enterprise , Automatically generate the enterprise supply and marketing relationship map of the enterprise to be queried, which ensures a comprehensive understanding of the actual supply and marketing relationship of the enterprise, avoids missing the enterprise supply and marketing relationship, and thus improves the accuracy of the obtained enterprise supply and marketing relationship.
  • the server can combine the enterprises to be queried and the obtained target enterprises of various layers to display to users in the form of an intelligent supply and marketing relationship atlas.
  • an enterprise supply and marketing relationship map corresponding to the enterprise to be queried is generated, which includes: taking the enterprise to be queried as the base-level target enterprise; And the obtained target enterprises of each layer are arranged in the first order to obtain the arranged target enterprises; according to the arranged target enterprises, the supply and marketing relationship between the target enterprises of the adjacent layers is obtained; according to the arranged target enterprises and the adjacent The supply and marketing relationship between the target enterprises at the tier generates an enterprise supply and marketing relationship atlas corresponding to the enterprise to be queried.
  • the server integrates the invoice information of many enterprises associated with the enterprise to be queried to generate the enterprise supply and marketing relationship atlas of the enterprise to be queried, which can cover the overall picture of the actual supply and marketing relationship of the enterprise to be queried, and further improves the accuracy of the acquired enterprise supply and marketing relationship; at the same time It is helpful for users to fully understand and master the actual supply and marketing relationship of the enterprise.
  • the basic target enterprises are ranked in the first column, and the target enterprises of the basic target enterprises are regarded as the first-tier target enterprises and ranked in the second column; the target enterprises of the first-tier target enterprises are regarded as the second-tier goals Enterprises, ranked in the third column; and so on, you can arrange the target enterprises at the grass-roots level and the target enterprises at each level obtained; traverse all the supply and marketing relationships between the target enterprises at adjacent levels, and combine the arranged target enterprises, you can Generate a supply and marketing relationship atlas corresponding to the enterprise to be queried.
  • each layer of target enterprises can include multiple target enterprises; the order of arrangement of multiple target enterprises in each layer of target enterprises is not specifically limited in this application.
  • the server may also generate an enterprise supply and marketing relationship atlas within a preset time range, such as the last three months, corresponding to the enterprise to be queried.
  • FIG. 5 another method for generating an enterprise supply and marketing relationship graph is provided, including the following steps:
  • Step S501 Receive an inquiry request sent by the terminal, where the inquiry request carries identification information of the enterprise to be queried and a preset time range.
  • Step S502 Query the database according to the identification information of the enterprise to be queried to obtain invoice information corresponding to the enterprise to be queried within a preset time range.
  • Step S503 Obtain the preset invoice information template; obtain the position label of the target enterprise's information in the preset invoice information template; determine the position to be extracted corresponding to the position label from the invoice information corresponding to the enterprise to be queried; extract to be extracted Information about the target business of the location.
  • Step S504 Obtain the invoice information corresponding to the target enterprise within the preset time range, and extract the information of the target enterprise again from the invoice information of the target enterprise; until the number of layers of the extracted target enterprise meets the set conditions.
  • Step S505 when the number of layers of the extracted target enterprise meets the set conditions, a business supply and marketing relationship map corresponding to the enterprise to be queried is generated within a preset time range according to the enterprise to be queried and the target enterprise at each layer obtained.
  • the above method for generating the supply-sales relationship graph of the enterprise realizes the generation of the supply-sales-relationship map corresponding to the enterprise to be queried within a preset time range based on the invoice information of many enterprises associated with the enterprise to be queried, which can cover the full picture of the actual supply-sales relationship of the enterprise to be queried , To further improve the accuracy of the obtained enterprise supply and marketing relationship.
  • step S205 after generating an enterprise supply and marketing relationship atlas corresponding to the enterprise to be queried, it further includes: dividing each target enterprise into different initial enterprise communities, and acquiring The module degree corresponding to the group; the module degree is generated according to the virtual structure corresponding to the enterprise community; the target enterprise is divided into the initial enterprise community adjacent to the target enterprise to obtain the intermediate enterprise community; the intermediate enterprise community is obtained Modularity, if the modularity is greater than that of the initial corporate community, the current division will be accepted; the target enterprise will be divided again into the intermediate corporate community adjacent to the target enterprise until the modularity of the obtained corporate community reaches the corresponding Threshold value; when the modularity of the obtained corporate community reaches the corresponding threshold, the obtained corporate community is obtained as the target corporate community.
  • the structure corresponding to the enterprise community is regarded as a virtual structure, and the modularity of the virtual structure corresponding to the enterprise community is calculated according to the existing FastUnfolding algorithm, which is not limited in this application. Modularity is used to describe the division results of enterprise communities. The closer the connections between enterprises in an enterprise community, the greater the corresponding modularity of the enterprise community.
  • the target enterprises in the corporate supply and marketing relationship graph can be divided into different corporate communities, which can effectively Identify the core business community of the company to be queried; at the same time, it is convenient for users to screen out the core business community closely related to the company with one click when querying a company, to avoid interference with redundant information, and further improve the accuracy of the obtained company supply and marketing relationship degree.
  • the method for generating a supply-sales relationship graph of an enterprise further includes: acquiring the target enterprise in the same target enterprise community; identifying the lower-level target enterprise of the target enterprise, acquiring the initial important value of the lower-level target enterprise and the target enterprise and the lower-level target enterprise The number of transactions between; according to the corresponding relationship between the number of transactions and the weight, determine the weight corresponding to the number of transactions obtained; based on the initial importance value and weight of the lower target enterprise, obtain the target important value of the lower target enterprise; obtain each lower target enterprise The sum of the target important values is taken as the important value of the target company, and the importance level corresponding to the important value of the target company is determined.
  • company A has 3 lower-level target companies, namely A1 company, A2 company, and A3 company; comprehensively evaluate the operating scale of the three lower-level target companies, and determine the importance of A1 company, A2 company, and A3 company.
  • the method for generating an enterprise supply and marketing relationship graph further includes: acquiring historical invoice information of the target enterprise within a preset time range; generating invoice verification files corresponding to the target enterprise based on the historical invoice information; and according to the invoice verification files, Verify the invoice information of the target enterprise; if the invoice information is verified incorrectly, generate a corresponding warning message and send the warning message to the corresponding target enterprise.
  • the server analyzes the target value of the invoice information (such as the value on the invoice and the number of invoices) of the target company within the preset time range to obtain the analysis result; obtains the approximate range of the target value based on the analysis result and generates the corresponding invoice verification Documents; verify the invoice information of the target company according to the invoice verification file, which can accurately identify abnormal invoice information, such as abnormally high invoice quantity, abnormally low invoice quantity, abnormally high value on the invoice, abnormally low value on the invoice, etc .; Generate the corresponding warning message, and send the warning message to the mobile phone of the person in charge of the enterprise through the SMS server to remind the person in charge of the enterprise to take corresponding measures to avoid unnecessary economic losses. Even, the server can combine the generated enterprise supply and marketing relationship atlas to determine the influence scope of the target enterprise.
  • the method for generating an enterprise supply and marketing relationship graph further includes: extracting the target enterprise in the generated enterprise supply and marketing relationship graph; obtaining basic information corresponding to each target enterprise; and integrating the enterprise supply and marketing relationship graph and the basic information of each target enterprise , Load into the preset supply and marketing relationship report template in the second order to generate the supply and marketing relationship report of the enterprise to be queried.
  • the basic information of an enterprise includes the industry, registered capital, and identity of the enterprise.
  • the server loads the enterprise supply and sales relationship map and the basic information of each target company into the preset supply and sales relationship report template in order of the enterprise supply and marketing relationship map first and the basic information of each target company in the order, to generate the supply and marketing relationship of the enterprise to be queried
  • the report can facilitate users to intuitively understand the overall picture of the enterprise's supply and marketing relationship of the enterprise to be queried, further strengthen the comprehensive understanding of the actual supply and marketing relationship of the inquiring enterprise, avoid missing the enterprise's supply and marketing relationship, and thus improve the accuracy of the acquired enterprise's supply and marketing relationship.
  • the present application provides a graph generation system, which includes a graph display module, an enterprise classification module, a grade classification module, an abnormality warning module, and a conclusion display module.
  • the graph display module contains two options, namely the company name option and the time range option; the graph display module is used to obtain the invoice information of the company in the selected time range according to the user name and time range selected by the user, and generate and display the time range
  • the enterprise supply and marketing relationship map corresponding to the enterprise.
  • the enterprise division module is used to divide the enterprises in the inquired enterprise supply and marketing relationship graph into different enterprise communities.
  • the grade division module is used to identify the important grades of enterprises in the same enterprise community, and divide the enterprises into "core enterprises", "important enterprises” and “ordinary enterprises” according to the important grades.
  • the abnormality early warning module is used to verify the invoice information of the enterprises in the inquired enterprise supply and marketing relationship atlas, and give an early warning to enterprises with abnormal invoice information.
  • the display module is used to push the characteristics of the enterprise's production and operation, development trajectory, and business risk in the inquired enterprise supply and marketing relationship graph to the user through the form of a message.
  • the user selects the name of the enterprise and the time range to query the enterprise supply and marketing relationship atlas within that time range.
  • the terminal responds to the user's selection of the company name and time range on the operation interface in the map generation system, generates a corresponding query request, and sends the query request to the server;
  • the server parses the query request to obtain the company name and time range selected by the user Query the database according to the name of the enterprise to obtain the invoice information corresponding to the enterprise in the time range; extract the information of the target enterprise from the invoice information corresponding to the enterprise; obtain the invoice information corresponding to the target enterprise in the time range from the target enterprise
  • the information of the target company is extracted again from the invoice information; until the number of layers of the extracted target company meets the set conditions; when the number of layers of the extracted target company meets the set conditions, it is generated according to the company and the target companies of each layer obtained
  • steps in the flowcharts of FIGS. 2, 3 and 5 are displayed in order according to the arrows, the steps are not necessarily executed in the order indicated by the arrows. Unless clearly stated in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least some of the steps in FIGS. 2, 3, and 5 may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but may be executed at different times. These sub-steps Or the execution order of the stages is not necessarily sequential, but may be executed in turn or alternately with other steps or sub-steps of the other steps or at least a part of the stages.
  • an apparatus for generating a supply and marketing relationship graph of an enterprise including: a request receiving module 710, an information query module 720, a first information extraction module 730, a second information extraction module 740 and Atlas generation module 750, in which:
  • the request receiving module 710 is used to receive the query request sent by the terminal, and the query request carries the identification information of the enterprise to be queried.
  • the information query module 720 is used to query the database according to the identification information of the enterprise to be queried to obtain invoice information corresponding to the enterprise to be queried.
  • the first information extraction module 730 is used to extract the information of the target enterprise from the invoice information corresponding to the enterprise to be queried.
  • the second information extraction module 740 is used to obtain the invoice information of the target enterprise, and extract the information of the target enterprise again from the invoice information of the target enterprise; until the number of layers of the extracted target enterprise meets the set condition.
  • the graph generation module 750 is configured to generate an enterprise supply and marketing relationship atlas corresponding to the to-be-queried enterprise according to the to-be-queried enterprise and the obtained target enterprise of each layer when the extracted target enterprise's layer number meets the set condition.
  • the first information extraction module is further used to obtain the preset invoice information template; obtain the location label of the target enterprise's information in the preset invoice information template; and determine from the invoice information corresponding to the enterprise to be queried The location to be extracted corresponding to the location label; extract the information of the target enterprise of the location to be extracted.
  • the graph generation module is further used to select the enterprise to be queried as a base-level target enterprise; arrange the base-level target enterprise and the obtained target enterprise in each order according to the first order to obtain the ranked target enterprise;
  • the arranged target enterprises obtain the supply and marketing relations between the target enterprises in the adjacent layer; according to the supply and marketing relations between the arranged target enterprises and the target enterprises in the adjacent layer, the enterprise supply and marketing relationship map corresponding to the enterprise to be queried is generated.
  • the enterprise supply and marketing map generation device further includes a target enterprise division module for generating an enterprise supply and marketing relationship map corresponding to the enterprise to be queried by the map generation module, and then dividing each target enterprise into a different initial enterprise community And obtain the module degree corresponding to each initial enterprise community; the module degree is generated according to the virtual structure corresponding to the enterprise community; the target enterprise is divided into the initial enterprise community adjacent to the target enterprise to obtain the intermediate enterprise community ; Obtain the module degree of the intermediate enterprise community, if the module degree is greater than that of the initial enterprise community, accept this division; divide the target enterprise into the intermediate enterprise community adjacent to the target enterprise again until the obtained enterprise The modularity of the community reaches the corresponding threshold; when the obtained modularity of the corporate community reaches the corresponding threshold, the obtained corporate community is obtained as the target corporate community.
  • a target enterprise division module for generating an enterprise supply and marketing relationship map corresponding to the enterprise to be queried by the map generation module, and then dividing each target enterprise into a different initial enterprise community And obtain the module degree corresponding to each
  • the enterprise supply and marketing relationship graph generation device further includes a rank acquisition module for acquiring target enterprises in the same target enterprise community; identifying the target enterprise's lower-level target enterprise, and acquiring the initial important value and target of the lower-level target enterprise The number of transactions between the enterprise and the lower-level target enterprise; according to the correspondence between the number of transactions and the weight, determine the weight corresponding to the acquired number of transactions; based on the initial importance value and weight of the lower-level target enterprise, the goal importance of the lower-level target enterprise is obtained Value; Obtain the sum of the target important values of each lower-level target enterprise as the target enterprise's important value, and determine the importance level corresponding to the target enterprise's important value.
  • the invoice verification module of the enterprise supply and marketing relationship graph generation device is used to obtain the historical invoice information of the target enterprise within a preset time range; based on the historical invoice information, an invoice verification file corresponding to the target enterprise is generated; based on the invoice The verification file verifies the invoice information of the target enterprise; if the invoice information is incorrectly verified, a corresponding warning message is generated and sent to the corresponding target enterprise.
  • the enterprise supply and marketing relationship graph generating device further includes a report generation module for extracting the target enterprise in the generated enterprise supply and marketing relationship graph; obtaining basic information corresponding to each target enterprise; and comparing the enterprise supply and marketing relationship graph and each The basic information of the target enterprise is loaded into the preset supply and marketing relationship report template in the second order to generate the supply and marketing relationship report of the enterprise to be queried.
  • the enterprise supply and sales relationship graph generation device achieves the purpose of continuously extracting the target enterprise from the enterprise's invoice information to obtain the enterprise's multi-layer supply and marketing relationship, avoiding the traditional method that can only obtain the enterprise's single-layer supply and marketing relationship.
  • the defects ensure a comprehensive understanding of the actual supply and marketing relationship of the enterprise, thereby improving the accuracy of the obtained enterprise supply and marketing relationship.
  • Each module in the above-mentioned enterprise supply and marketing relationship graph generation device may be implemented in whole or in part by software, hardware, and a combination thereof.
  • the above modules may be embedded in the hardware or independent of the processor in the computer device, or may be stored in the memory in the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.
  • a computer device is provided.
  • the computer device may be a server, and an internal structure diagram thereof may be as shown in FIG. 7.
  • the computer device includes a processor, memory, network interface, and database connected by a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities.
  • the memory of the computer device includes a non-volatile computer-readable storage medium and internal memory.
  • the non-volatile computer-readable storage medium stores an operating system, computer-readable instructions, and a database.
  • the internal memory provides an environment for the operation of the operating system and computer-readable instructions in the non-volatile computer-readable storage medium.
  • the database of the computer device is used to store invoice information.
  • the network interface of the computer device is used to communicate with external terminals through a network connection.
  • FIG. 7 is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied.
  • the specific computer device may Include more or less components than shown in the figure, or combine certain components, or have a different arrangement of components.
  • a computer device includes a memory and one or more processors.
  • the memory stores computer-readable instructions.
  • the one or more processors perform the following steps:
  • the query request carries the identification information of the enterprise to be queried
  • a supply and marketing relationship atlas corresponding to the enterprise to be queried is generated according to the enterprise to be queried and the target enterprise at each layer obtained.
  • the processor also implements the following steps when executing the computer-readable instructions: acquiring the preset invoice information template; acquiring the position label of the target enterprise's information in the preset invoice information template; In the invoice information, determine the location to be extracted corresponding to the location label; and extract the information of the target company of the location to be extracted.
  • the processor executes the computer-readable instructions, the following steps are further implemented: the enterprise to be queried is regarded as the base-level target enterprise; the base-level target enterprise and the obtained target-level enterprise are arranged in the first order, after the arrangement Target companies; according to the ranked target companies, obtain the supply and marketing relationship between the target companies in the adjacent layer; and according to the supply and marketing relationship between the aligned target companies and the target companies in the adjacent layer, generate a correspondence with the enterprises to be queried Of the enterprise's supply and marketing relationship.
  • the processor also implements the following steps when executing the computer-readable instructions: after generating the enterprise supply and marketing relationship map corresponding to the enterprise to be queried, each target enterprise is divided into different initial enterprise communities, and Obtain the module degree corresponding to each initial enterprise community; the module degree is generated according to the virtual structure corresponding to the enterprise community; divide the target enterprise into the initial enterprise community adjacent to the target enterprise to obtain the intermediate enterprise community; obtain the intermediate The modularity of the corporate community, if the modularity is greater than that of the initial corporate community, this division will be accepted; the target enterprise will be divided again into the intermediate corporate community adjacent to the target enterprise until the The module degree reaches the corresponding threshold; and when the obtained module degree of the enterprise community reaches the corresponding threshold, the obtained enterprise community is obtained as the target enterprise community.
  • the processor also implements the following steps when executing the computer-readable instructions: acquiring the target enterprise in the same target enterprise community; identifying the lower-level target enterprise of the target enterprise, and acquiring the initial important value of the lower-level target enterprise and the target enterprise The number of transactions with the lower-level target enterprise; according to the correspondence between the number of transactions and the weight, determine the weight corresponding to the acquired transaction number; based on the initial importance value of the lower-level target enterprise and the weight, the target important value of the lower-level target enterprise is obtained ; And obtain the sum of the target important values of each lower-level target company as the target company's important value, and determine the importance level corresponding to the target company's important value.
  • the processor also implements the following steps when executing computer-readable instructions: acquiring historical invoice information of the target enterprise within a preset time range; generating invoice verification files corresponding to the target enterprise based on the historical invoice information; The invoice verification document verifies the invoice information of the target enterprise; and if the invoice information verification is incorrect, a corresponding warning message is generated and sent to the corresponding target enterprise.
  • the processor also implements the following steps when executing the computer-readable instructions: extracting the target enterprise in the generated enterprise supply and marketing relationship atlas; obtaining basic information corresponding to each target enterprise; and integrating the enterprise supply and marketing relationship atlas and each The basic information of the target enterprise is loaded into the preset supply and marketing relationship report template in the second order to generate the supply and marketing relationship report of the enterprise to be queried.
  • the computer device realizes the purpose of continuously extracting the target enterprise from the invoice information of the enterprise through the computer-readable instructions running on the processor to obtain the multi-layered supply and marketing relationship of the enterprise, avoiding the traditional method of obtaining
  • the defects of the single-layer supply and marketing relationship of the enterprise ensure a comprehensive understanding of the actual supply and marketing relationship of the enterprise, thereby improving the accuracy of the obtained enterprise supply and marketing relationship.
  • One or more non-volatile computer-readable storage media storing computer-readable instructions.
  • the computer-readable instructions When executed by one or more processors, the one or more processors perform the following steps:
  • the query request carries the identification information of the enterprise to be queried
  • a supply and marketing relationship atlas corresponding to the enterprise to be queried is generated according to the enterprise to be queried and the target enterprise at each layer obtained.
  • the following steps are also achieved: obtaining a preset invoice information template; obtaining a position label of the target enterprise's information in the preset invoice information template; In the invoice information, determine the location to be extracted corresponding to the location label; and extract the information of the target company of the location to be extracted.
  • the enterprise to be queried is regarded as the base-level target enterprise; the base-level target enterprise and the obtained target-level enterprise are arranged in the first order to obtain the arrangement After the target enterprises, according to the arranged target enterprises, obtain the supply and marketing relationship between the target companies in the adjacent layer; and according to the supply and marketing relationship between the aligned target enterprises and the adjacent layer of target companies, generate and query enterprises Corresponding enterprise supply and marketing relationship atlas.
  • each target enterprise is divided into different initial enterprise communities, And obtain the module degree corresponding to each initial enterprise community; the module degree is generated according to the virtual structure corresponding to the enterprise community; the target enterprise is divided into the initial enterprise community adjacent to the target enterprise to obtain the intermediate enterprise community; obtain The modularity of the intermediate enterprise community, if the modularity is greater than the initial enterprise community, accept this division; divide the target enterprise into the intermediate enterprise community adjacent to the target enterprise again, until the obtained enterprise community The degree of modularity reaches the corresponding threshold; and when the degree of modularity of the obtained enterprise community reaches the corresponding threshold, the obtained enterprise community is obtained as the target enterprise community.
  • the following steps are also achieved: acquiring the target enterprise in the same target enterprise community; identifying the lower-level target enterprise of the target enterprise, and acquiring the initial important value and target of the lower-level target enterprise The number of transactions between the enterprise and the lower target enterprise; according to the correspondence between the number of transactions and the weight, the weight corresponding to the acquired transaction number is determined; based on the initial importance value and weight of the lower target enterprise, the target important value of the lower target enterprise is obtained; And obtain the sum of the target important values of each lower-level target company as the target company's important value, and determine the importance level corresponding to the target company's important value.
  • the following steps are also achieved: acquiring historical invoice information of the target enterprise within a preset time range; generating invoice verification files corresponding to the target enterprise based on the historical invoice information; According to the invoice verification document, verify the invoice information of the target enterprise; and if the invoice information verification is incorrect, generate a corresponding warning message and send the warning message to the corresponding target enterprise.
  • the computer-readable instructions are executed by the processor to implement the following steps: extract target enterprises in the generated enterprise supply and marketing relationship atlas; obtain basic information corresponding to each target enterprise; and convert the enterprise supply and marketing relationship atlas and The basic information of each target enterprise is loaded into the preset supply and marketing relationship report template in the second order to generate the supply and marketing relationship report of the enterprise to be queried.
  • the non-volatile computer-readable storage medium uses the computer-readable instructions stored therein to achieve the purpose of continuously extracting the target enterprise from the enterprise's invoice information to obtain the enterprise's multi-layer supply and marketing relationship, avoiding the The method can only obtain the defects of the single-layer supply and marketing relationship of the enterprise, which ensures a comprehensive understanding of the actual supply and marketing relationship of the enterprise, thereby improving the accuracy of the obtained enterprise supply and marketing relationship.
  • Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory.
  • Volatile memory can include random access memory (RAM) or external cache memory.
  • RAM random access memory
  • DRAM dynamic RAM
  • SDRAM synchronous DRAM
  • DDRSDRAM double data rate SDRAM
  • ESDRAM enhanced SDRAM
  • SLDRAM synchronous chain (Synchlink) DRAM
  • RDRAM direct RAM
  • DRAM direct memory bus dynamic RAM
  • RDRAM memory bus dynamic RAM

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • Data Mining & Analysis (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Software Systems (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

一种企业供销关系图谱生成方法，包括：接收终端发送的查询请求，查询请求携带待查询企业的标识信息；根据待查询企业的标识信息查询数据库，获取与待查询企业对应的发票信息；从与待查询企业对应的发票信息中提取目标企业的信息；获取目标企业的发票信息，从目标企业的发票信息中再次提取目标企业的信息；直到提取到的目标企业的层数满足设定条件；当提取到的目标企业的层数满足设定条件时，根据待查询企业以及得到的各层目标企业，生成与待查询企业对应的企业供销关系图谱。

Description

企业供销关系图谱生成方法、装置和计算机设备
本申请要求于2018年10月17日提交中国专利局，申请号为2018112107440，申请名称为“企业供销关系图谱生成方法、装置和计算机设备”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本申请涉及一种企业供销关系图谱生成方法、装置和计算机设备。
背景技术
随着互联网技术的发展，企业与企业之间的联系越来越密切，对企业信息，特别是企业的供销状况的了解显得越来越重要。
然而，对于企业的供销状况，在传统的方法中，服务器往往只能对一家企业的一层上下游关系的数据进行计算分析，并得到单一的企业供销关系图谱。但是，发明人意识到，传统方法得到的企业供销关系图谱，难以覆盖所述企业的实际供销体系全貌，造成无法真正地了解企业的实际供销关系，导致获取的企业供销关系的准确度低。
发明内容
根据本申请公开的各种实施例，提供一种企业供销关系图谱生成方法、装置和计算机设备。
一种企业供销关系图谱生成方法包括：
接收终端发送的查询请求，所述查询请求携带待查询企业的标识信息；
根据所述待查询企业的标识信息查询数据库，获取与所述待查询企业对应的发票信息；
从与所述待查询企业对应的发票信息中提取目标企业的信息；
获取所述目标企业的发票信息，从所述目标企业的发票信息中再次提取目标企业的信息；直到提取到的目标企业的层数满足设定条件；及
当提取到的目标企业的层数满足设定条件时，根据所述待查询企业以及得到的各层目标企业，生成与所述待查询企业对应的企业供销关系图谱。
一种企业供销关系图谱生成装置包括：
请求接收模块，用于接收终端发送的查询请求，所述查询请求携带待查询企业的标识信息；
信息查询模块，用于根据所述待查询企业的标识信息查询数据库，获取与所述待查询企业对应的发票信息；
第一信息提取模块，用于从与所述待查询企业对应的发票信息中提取目标企业的信息；
第二信息提取模块，用于获取所述目标企业的发票信息，从所述目标企业的发票信息 中再次提取目标企业的信息；直到提取到的目标企业的层数满足设定条件；及
图谱生成模块，用于当提取到的目标企业的层数满足设定条件时，根据所述待查询企业以及得到的各层目标企业，生成与所述待查询企业对应的企业供销关系图谱。
一种计算机设备，包括存储器和一个或多个处理器，所述存储器中储存有计算机可读指令，所述计算机可读指令被所述处理器执行时，使得所述一个或多个处理器执行以下步骤：
接收终端发送的查询请求，所述查询请求携带待查询企业的标识信息；
根据所述待查询企业的标识信息查询数据库，获取与所述待查询企业对应的发票信息；
从与所述待查询企业对应的发票信息中提取目标企业的信息；
获取所述目标企业的发票信息，从所述目标企业的发票信息中再次提取目标企业的信息；直到提取到的目标企业的层数满足设定条件；及
当提取到的目标企业的层数满足设定条件时，根据所述待查询企业以及得到的各层目标企业，生成与所述待查询企业对应的企业供销关系图谱。
在其中一个实施例中，处理器执行计算机可读指令时还实现以下步骤：获取预设发票信息模板；获取目标企业的信息在预设发票信息模板中的位置标签；从与待查询企业对应的发票信息中，确定与位置标签对应的待提取位置；及提取待提取位置的目标企业的信息。
在其中一个实施例中，处理器执行计算机可读指令时还实现以下步骤：将待查询企业作为基层目标企业；将基层目标企业以及得到的各层目标企业按照第一顺序进行排列，得到排列后的目标企业；根据排列后的目标企业，获取相邻层的目标企业之间的供销关系；及根据排列后的目标企业以及相邻层的目标企业之间的供销关系，生成与待查询企业对应的企业供销关系图谱。
在其中一个实施例中，处理器执行计算机可读指令时还实现以下步骤：在生成与待查询企业对应的企业供销关系图谱之后，将每个目标企业划分到不同的初始企业社群中，并获取与各个初始企业社群对应的模块度；模块度根据企业社群所对应的虚拟结构生成；将目标企业划分到与目标企业相邻的初始企业社群中，得到中间企业社群；获取中间企业社群的模块度，若模块度大于初始企业社群的模块度，则接受本次划分；将目标企业再次划分到与目标企业相邻的中间企业社群中，直到得到的企业社群的模块度达到对应的阈值；及当得到的企业社群的模块度达到对应的阈值时，获取得到的企业社群，作为目标企业社群。
在其中一个实施例中，处理器执行计算机可读指令时还实现以下步骤：获取同一目标企业社群中的目标企业；识别目标企业的下层目标企业，获取下层目标企业的初始重要值以及目标企业与下层目标企业之间的交易次数；根据交易次数与权重的对应关系，确定与获取的交易次数对应的权重；根据下层目标企业的初始重要值和所述权重，得到下层目标企业的目标重要值；及获取各个下层目标企业的目标重要值之和，作为目标企业的重要值，并确定与目标企业的重要值对应的重要等级。
在其中一个实施例中，处理器执行计算机可读指令时还实现以下步骤：获取目标企业在预设时间范围内的历史发票信息；根据历史发票信息，生成与目标企业对应的发票验证文件；根据发票验证文件，对目标企业的发票信息进行验证；及若发票信息验证错误，则生成相应的预警消息，并将预警消息发送至对应的目标企业。
在其中一个实施例中，处理器执行计算机可读指令时还实现以下步骤：提取生成的企业供销关系图谱中的目标企业；获取与各个目标企业对应的基本信息；及将企业供销关系图谱和各个目标企业的基本信息，按照第二顺序加载到预设供销关系报告模板中，生成待查询企业的供销关系报告。
一个或多个存储有计算机可读指令的非易失性计算机可读存储介质，计算机可读指令被一个或多个处理器执行时，使得一个或多个处理器执行以下步骤：
接收终端发送的查询请求，所述查询请求携带待查询企业的标识信息；
根据所述待查询企业的标识信息查询数据库，获取与所述待查询企业对应的发票信息；
从与所述待查询企业对应的发票信息中提取目标企业的信息；
获取所述目标企业的发票信息，从所述目标企业的发票信息中再次提取目标企业的信息；直到提取到的目标企业的层数满足设定条件；及
当提取到的目标企业的层数满足设定条件时，根据所述待查询企业以及得到的各层目标企业，生成与所述待查询企业对应的企业供销关系图谱。
在其中一个实施例中，计算机可读指令被处理器执行时还实现以下步骤：获取预设发票信息模板；获取目标企业的信息在预设发票信息模板中的位置标签；从与待查询企业对应的发票信息中，确定与位置标签对应的待提取位置；及提取待提取位置的目标企业的信息。
在其中一个实施例中，计算机可读指令被处理器执行时还实现以下步骤：将待查询企业作为基层目标企业；将基层目标企业以及得到的各层目标企业按照第一顺序进行排列，得到排列后的目标企业；根据排列后的目标企业，获取相邻层的目标企业之间的供销关系；及根据排列后的目标企业以及相邻层的目标企业之间的供销关系，生成与待查询企业对应的企业供销关系图谱。
在其中一个实施例中，计算机可读指令被处理器执行时还实现以下步骤：在生成与待查询企业对应的企业供销关系图谱之后，将每个目标企业划分到不同的初始企业社群中，并获取与各个初始企业社群对应的模块度；模块度根据企业社群所对应的虚拟结构生成；将目标企业划分到与目标企业相邻的初始企业社群中，得到中间企业社群；获取中间企业社群的模块度，若模块度大于初始企业社群的模块度，则接受本次划分；将目标企业再次划分到与目标企业相邻的中间企业社群中，直到得到的企业社群的模块度达到对应的阈值；及当得到的企业社群的模块度达到对应的阈值时，获取得到的企业社群，作为目标企业社群。
在其中一个实施例中，计算机可读指令被处理器执行时还实现以下步骤：获取同一目 标企业社群中的目标企业；识别目标企业的下层目标企业，获取下层目标企业的初始重要值以及目标企业与下层目标企业之间的交易次数；根据交易次数与权重的对应关系，确定与获取的交易次数对应的权重；根据下层目标企业的初始重要值和权重，得到下层目标企业的目标重要值；及获取各个下层目标企业的目标重要值之和，作为目标企业的重要值，并确定与目标企业的重要值对应的重要等级。
在其中一个实施例中，计算机可读指令被处理器执行时还实现以下步骤：获取目标企业在预设时间范围内的历史发票信息；根据历史发票信息，生成与目标企业对应的发票验证文件；根据发票验证文件，对目标企业的发票信息进行验证；及若发票信息验证错误，则生成相应的预警消息，并将预警消息发送至对应的目标企业。
在其中一个实施例中，计算机可读指令被处理器执行时还实现以下步骤：提取生成的企业供销关系图谱中的目标企业；获取与各个目标企业对应的基本信息；及将企业供销关系图谱和各个目标企业的基本信息，按照第二顺序加载到预设供销关系报告模板中，生成待查询企业的供销关系报告。
本申请的一个或多个实施例的细节在下面的附图和描述中提出。本申请的其他特征和优点将从说明书、附图以及权利要求书变得明显。
附图说明
为了更清楚地说明本申请实施例中的技术方案，下面将对实施例中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本申请的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其它的附图。
图1为根据一个或多个实施例中企业供销关系图谱生成方法的应用场景图。
图2为根据一个或多个实施例中企业供销关系图谱生成方法的流程示意图。
图3为根据一个或多个实施例中从与待查询企业对应的发票信息中提取目标企业的信息的步骤的流程示意图。
图4为根据一个或多个实施例中企业供销关系图谱的示意图。
图5为另一个实施例中企业供销关系图谱生成方法的流程示意图。
图6为根据一个或多个实施例中图谱生成系统的框图。
图7为根据一个或多个实施例中企业供销关系图谱生成装置的框图。
图8为根据一个或多个实施例中计算机设备的框图。
具体实施方式
为了使本申请的技术方案及优点更加清楚明白，以下结合附图及实施例，对本申请进行进一步详细说明。应当理解，此处描述的具体实施例仅仅用以解释本申请，并不用于限定本申请。
本申请提供的企业供销关系图谱生成方法，可以应用于如图1所示的应用环境中。终 端110与服务器120通过网络进行通信。终端110安装了图谱生成系统；终端110通过识别用户在图谱生成系统对应的操作界面上的输入操作，生成查询请求，并将查询请求发送至服务器120；查询请求携带用户输入的待查询企业的标识信息。服务器120解析查询请求，得到待查询企业的标识信息；根据待查询企业的标识信息查询数据库，获取与待查询企业对应的发票信息；从与待查询企业对应的发票信息中提取目标企业的信息；获取目标企业的发票信息，从目标企业的发票信息中再次提取目标企业的信息；直到提取到的目标企业的层数满足设定条件；当提取到的目标企业的层数满足设定条件时，根据待查询企业以及得到的各层目标企业，生成与待查询企业对应的企业供销关系图谱，并将生成的企业供销关系图谱发送至终端110中。终端110可以但不限于是各种个人计算机、笔记本电脑、智能手机和平板电脑，服务器120可以用独立的服务器或者是多个服务器组成的服务器集群来实现。
在其中一个实施例中，如图2所示，提供了一种企业供销关系图谱生成方法，以该方法应用于图1中的服务器为例进行说明，包括以下步骤：
步骤S201，接收终端发送的查询请求，查询请求携带待查询企业的标识信息。
待查询企业的标识信息是指用来对企业进行标识的信息，便于服务器进行区分；比如企业名称，企业代码，企业负责人身份证号码等，具体本申请不做限定。
终端安装了图谱生成系统，图谱生成系统可以用于生成企业供销关系图谱。终端通过响应用户在图谱生成系统对应的操作界面上的输入操作，生成对应的查询请求，并将查询请求发送至服务器；查询请求携带用户输入的待查询企业的标识信息。服务器接收终端发送的查询请求，根据查询请求，得到待查询企业的标识信息。
步骤S202，根据待查询企业的标识信息查询数据库，获取与待查询企业对应的发票信息。
服务器基于大数据，获取不同企业的历史发票信息，将历史发票信息按照企业的标识信息，分类存储至预先建立的数据库中，方便后续查找与待查询企业对应的发票信息。
服务器解析终端发送的查询请求，得到待查询企业的标识信息；根据待查询企业的标识信息查询数据库，获取标识信息与待查询企业的标识信息匹配的发票信息，作为与待查询企业对应的发票信息。
步骤S203，从与待查询企业对应的发票信息中提取目标企业的信息。
发票信息含有销售方和购买方的信息，目标企业是指购买方，且目标企业在发票信息中的位置是固定的。比如，在与待查询企业对应的发票信息中，待查询企业是指销售方，目标企业是指购买方。
服务器获取企业发票信息模板，根据企业发票信息模板中的目标企业的信息的位置，确定待查询企业的发票信息中对应的待提取位置，并获取待提取位置的目标企业的信息。从待查询企业的发票信息中，获取目标企业的信息，有利于覆盖待查询企业的目标企业，避免遗漏目标企业，进一步提高了获取的企业供销关系的准确度。
步骤S204，获取目标企业的发票信息，从目标企业的发票信息中再次提取目标企业的信息；直到提取到的目标企业的层数满足设定条件。
服务器获取待查询企业的目标企业的发票信息，从目标企业的发票信息中再次提取目标企业的信息，以此类推，直到提取到的目标企业的层数满足设定条件；实现了不断从企业的发票信息中提取目标企业，以获取企业的多层供销关系的目的，避免了传统方法中只能获取企业的单层供销关系的缺陷，进一步提高了获取的企业供销关系的准确度。
步骤S205，当提取到的目标企业的层数满足设定条件时，根据待查询企业以及得到的各层目标企业，生成与待查询企业对应的企业供销关系图谱。
服务器不断从企业的发票信息中提取目标企业信息，并对提取到的目标企业的层数进行统计；当确定提取到的目标企业的层数满足设定条件时，服务器根据待查询企业以及得到的各层目标企业，生成与待查询企业对应的企业供销关系图谱，能够覆盖待查询企业的实际供销关系全貌，进一步提高了获取的企业供销关系的准确度。
上述企业供销关系图谱生成方法中，服务器接收终端发送的查询请求，根据查询请求携带的待查询企业的标识信息查询数据库，获取与待查询企业对应的发票信息；从与待查询企业对应的发票信息中提取目标企业的信息；获取目标企业的发票信息，从目标企业的发票信息中再次提取目标企业的信息；直到提取到的目标企业的层数满足设定条件；当提取到的目标企业的层数满足设定条件时，根据待查询企业以及得到的各层目标企业，生成与待查询企业对应的企业供销关系图谱；实现了不断从企业的发票信息中提取目标企业，以获取企业的多层供销关系的目的，避免了传统方法中只能获取企业的单层供销关系的缺陷，保证了对企业的实际供销关系的全面了解，避免遗漏企业供销关系，从而提高了获取的企业供销关系的准确度；同时将与待查询企业关联的众多企业的发票信息进行整合，生成待查询企业的企业供销关系图谱，能够覆盖待查询企业的实际供销关系全貌，进一步提高了获取的企业供销关系的准确度。
在其中一个实施例中，如图3所示，从与待查询企业对应的发票信息中提取目标企业的信息的步骤具体包括：
步骤S301，获取预设发票信息模板。
步骤S302，获取目标企业的信息在预设发票信息模板中的位置标签。
步骤S303，从与待查询企业对应的发票信息中，确定与位置标签对应的待提取位置。
步骤S304，提取待提取位置的目标企业的信息。
服务器通过预设发票信息模板中目标企业的信息的位置标签，确定发票信息中位置标签相对应的待提取位置，并获取待提取位置的目标企业的信息，方便后续根据提取到的目标企业的信息，自动生成待查询企业的企业供销关系图谱，保证了对企业的实际供销关系的全面了解，避免遗漏企业供销关系，从而提高了获取的企业供销关系的准确度。
在得到多层目标企业之后，为了方便用户查看待查询企业的实际供销关系全貌，服务器可以结合待查询企业以及得到的各层目标企业，以智能供销关系图谱的形式向用户展示。
在其中一个实施例中，上述步骤S205，根据待查询企业以及得到的各层目标企业，生成与待查询企业对应的企业供销关系图谱，包括：将待查询企业作为基层目标企业；将基层目标企业以及得到的各层目标企业按照第一顺序进行排列，得到排列后的目标企业；根据排列后的目标企业，获取相邻层的目标企业之间的供销关系；根据排列后的目标企业以及相邻层的目标企业之间的供销关系，生成与待查询企业对应的企业供销关系图谱。服务器将与待查询企业关联的众多企业的发票信息进行整合，生成待查询企业的企业供销关系图谱，能够覆盖待查询企业的实际供销关系全貌，进一步提高了获取的企业供销关系的准确度；同时有利于用户全面了解和掌握企业的实际供销关系。
如图4所示，将基层目标企业排在第一列，将基层目标企业的目标企业作为第一层目标企业，排在第二列；将第一层目标企业的目标企业作为第二层目标企业，排在第三列；以此类推，可以将基层目标企业以及得到的各层目标企业进行排列；遍历相邻层的目标企业之间的全部供销关系，并结合排列后的目标企业，可以生成与待查询企业对应的企业供销关系图谱。需要说明的是，每一层目标企业可以包含多个目标企业；针对每一层目标企业中的多个目标企业的排列顺序，本申请不做具体限定。
进一步地，为了保证生成的企业供销关系图谱的时效性，服务器还可以生成预设时间范围内，比如最近三个月，与待查询企业对应的企业供销关系图谱。
在其中一个实施例中，如图5所示，提供了另一种企业供销关系图谱生成方法，包括以下步骤：
步骤S501，接收终端发送的查询请求，查询请求携带待查询企业的标识信息和预设时间范围。
步骤S502，根据待查询企业的标识信息查询数据库，获取预设时间范围的与待查询企业对应的发票信息。
步骤S503，获取预设发票信息模板；获取目标企业的信息在预设发票信息模板中的位置标签；从与待查询企业对应的发票信息中，确定与位置标签对应的待提取位置；提取待提取位置的目标企业的信息。
步骤S504，获取预设时间范围的与目标企业对应的发票信息，从目标企业的发票信息中再次提取目标企业的信息；直到提取到的目标企业的层数满足设定条件。
步骤S505，当提取到的目标企业的层数满足设定条件时，根据待查询企业以及得到的各层目标企业，生成预设时间范围的与待查询企业对应的企业供销关系图谱。
上述企业供销关系图谱生成方法，实现了根据与待查询企业关联的众多企业的发票信息，生成预设时间范围的与待查询企业对应的企业供销关系图谱，能够覆盖待查询企业的实际供销关系全貌，进一步提高了获取的企业供销关系的准确度。
在其中一个实施例中，上述步骤S205，在生成与待查询企业对应的企业供销关系图谱之后，还包括：将每个目标企业划分到不同的初始企业社群中，并获取与各个初始企业社群对应的模块度；模块度根据企业社群所对应的虚拟结构生成；将目标企业划分到与目 标企业相邻的初始企业社群中，得到中间企业社群；获取所述中间企业社群的模块度，若模块度大于初始企业社群的模块度，则接受本次划分；将目标企业再次划分到与目标企业相邻的中间企业社群中，直到得到的企业社群的模块度达到对应的阈值；当得到的企业社群的模块度达到对应的阈值时，获取得到的企业社群，作为目标企业社群。
将企业社群所对应的结构当作虚拟结构，根据现有的FastUnfolding算法计算企业社群所对应的虚拟结构的模块度，具体本申请不做限定。模块度用于描述企业社群的划分结果，若一个企业社群中的企业之间的联系越紧密，则该企业社群对应的模块度越大。通过不断迭代计算各种划分结果下的企业社群的模块度，直到企业社群的模块度达到对应的阈值，可以将企业供销关系图谱中的目标企业划分到不同的企业社群中，能够有效识别出待查询企业的核心企业社群；同时方便用户在查询某家企业时一键筛选出与该企业密切相关的核心企业社群，避免多余信息干扰，进一步提高了获取的企业供销关系的准确度。
在其中一个实施例中，企业供销关系图谱生成方法还包括：获取同一目标企业社群中的目标企业；识别目标企业的下层目标企业，获取下层目标企业的初始重要值以及目标企业与下层目标企业之间的交易次数；根据交易次数与权重的对应关系，确定与获取的交易次数对应的权重；根据下层目标企业的初始重要值和权重，得到下层目标企业的目标重要值；获取各个下层目标企业的目标重要值之和，作为目标企业的重要值，并确定与目标企业的重要值对应的重要等级。
比如，A企业有3个下层目标企业，分别是A1企业、A2企业和A3企业；综合评估3个下层目标企业的经营规模，确定A1企业、A2企业和A3企业的重要性，依次对应的初始重要值分别是B1、B2和B3；基于大数据，确定A企业与A1企业的交易次数为C1，A企业与A2企业的交易次数为C2，以及A企业与A3企业的交易次数为C3；根据交易次数与权重的对应关系，确定交易次数C1对应的权重为D1，交易次数C2对应的权重为D2，以及交易次数C3对应的权重为D3；则A1企业的目标重要值S1＝B1×D1；A2企业的目标重要值S2＝B2×D2；A3企业的目标重要值S3＝B3×D3；根据目标企业的重要值为各个下层目标企业的目标重要值之和，确定A企业的重要值为S＝S1+S2+S3＝B1×D1+B2×D2+B3×D3；根据目标企业的重要值与重要等级对应关系，可以确定与A企业的重要值S对应的重要等级。比如，将企业的重要等级分成三个等级，分别是第一等级“核心企业”、第二等级“重要企业”和第三等级“普通企业”。
综合考虑目标企业的所有下层目标企业的重要性，以及目标企业与下层目标企业之间的交易次数，可以准确地识别目标企业在同一个企业社群的重要程度，方便用户快速了解目标企业的地位，加强了对目标企业的全面了解。
在其中一个实施例中，企业供销关系图谱生成方法还包括：获取目标企业在预设时间范围内的历史发票信息；根据历史发票信息，生成与目标企业对应的发票验证文件；根据发票验证文件，对目标企业的发票信息进行验证；若发票信息验证错误，则生成相应的预警消息，并将预警消息发送至对应的目标企业。
服务器通过对目标企业在预设时间范围内的发票信息的目标数值(比如发票上的数值、发票数量)进行分析，得到分析结果；根据分析结果获取目标数值的大致范围，并生成对应的发票验证文件；根据发票验证文件对目标企业的发票信息进行验证，可以准确识别出异常发票信息，比如发票数量异常高、发票数量异常低、发票上的数值异常高、发票上的数值异常低等；同时生成相应的预警消息，通过短信服务器将预警消息发送到企业负责人的手机中，以提醒企业负责人采取对应的措施，避免造成不必要的经济损失。甚至，服务器可以结合生成的企业供销关系图谱，确定目标企业的影响范围。
在其中一个实施例中，企业供销关系图谱生成方法还包括：提取生成的企业供销关系图谱中的目标企业；获取与各个目标企业对应的基本信息；将企业供销关系图谱和各个目标企业的基本信息，按照第二顺序加载到预设供销关系报告模板中，生成待查询企业的供销关系报告。企业的基本信息包括企业所属行业、注册资本、所属身份等。服务器按照企业供销关系图谱在前、各个目标企业的基本信息在后的顺序，依次将企业供销关系图谱和各个目标企业的基本信息加载到预设供销关系报告模板中，生成待查询企业的供销关系报告，可以方便用户直观了解待查询企业的企业供销关系全貌，进一步加强了对待查询企业的实际供销关系的全面了解，避免遗漏企业供销关系，从而提高了获取的企业供销关系的准确度。
在其中一个实施例中，如图6所示，本申请提供了一种图谱生成系统，该系统包含图谱展示模块、企业划分模块、等级划分模块、异常预警模块和结论展示模块。图谱展示模块包含两个选项，分别是企业名称选项和时间范围选项；图谱展示模块用于根据用户选取的企业名称和时间范围，获取企业在选取的时间范围的发票信息，生成并展示该时间范围的与企业对应的企业供销关系图谱。企业划分模块用于将查询到的企业供销关系图谱中的企业划分到不同的企业社群中。等级划分模块用于识别同一企业社群中的企业的重要等级，并根据重要等级，将企业划分为“核心企业”、“重要企业”和“普通企业”。异常预警模块用于对查询到的企业供销关系图谱中的企业的发票信息进行验证，并对发票信息存在异常的企业做出预警。结论展示模块用于将查询到的企业供销关系图谱中的企业的生产经营、发展轨迹、经营风险等方面的特征，通过消息的形式推送给用户。
在图谱生成系统的操作界面上，用户选择企业名称和时间范围，以查询该时间范围的企业供销关系图谱。终端响应用户对图谱生成系统中的操作界面上的企业名称和时间范围的选中操作，生成对应的查询请求，并将查询请求发送至服务器；服务器解析查询请求，得到用户选取的企业名称和时间范围；根据企业名称查询数据库，获取该时间范围的与企业对应的发票信息；从与企业对应的发票信息中提取目标企业的信息；获取该时间范围的与目标企业对应的发票信息，从目标企业的发票信息中再次提取目标企业的信息；直到提取到的目标企业的层数满足设定条件；当提取到的目标企业的层数满足设定条件时，根据企业以及得到的各层目标企业，生成该时间范围的与企业对应的企业供销关系图谱；实现了不断从企业的发票信息中提取目标企业，以获取企业的多层供销关系的目的，避免了传 统方法中只能获取企业的单层供销关系的缺陷，保证了对企业的实际供销关系的全面了解，避免遗漏企业供销关系，从而提高了获取的企业供销关系的准确度。
应该理解的是，虽然图2、3和5的流程图中的各个步骤按照箭头的指示依次显示，但是这些步骤并不是必然按照箭头指示的顺序依次执行。除非本文中有明确的说明，这些步骤的执行并没有严格的顺序限制，这些步骤可以以其它的顺序执行。而且，图2、3和5中的至少一部分步骤可以包括多个子步骤或者多个阶段，这些子步骤或者阶段并不必然是在同一时刻执行完成，而是可以在不同的时刻执行，这些子步骤或者阶段的执行顺序也不必然是依次进行，而是可以与其它步骤或者其它步骤的子步骤或者阶段的至少一部分轮流或者交替地执行。
在其中一个实施例中，如图7所示，提供了一种企业供销关系图谱生成装置，包括：请求接收模块710、信息查询模块720、第一信息提取模块730、第二信息提取模块740和图谱生成模块750，其中：
请求接收模块710，用于接收终端发送的查询请求，查询请求携带待查询企业的标识信息。
信息查询模块720，用于根据待查询企业的标识信息查询数据库，获取与待查询企业对应的发票信息。
第一信息提取模块730，用于从与待查询企业对应的发票信息中提取目标企业的信息。
第二信息提取模块740，用于获取目标企业的发票信息，从目标企业的发票信息中再次提取目标企业的信息；直到提取到的目标企业的层数满足设定条件。
图谱生成模块750，用于当提取到的目标企业的层数满足设定条件时，根据待查询企业以及得到的各层目标企业，生成与待查询企业对应的企业供销关系图谱。
在其中一个实施例中，第一信息提取模块还用于获取预设发票信息模板；获取目标企业的信息在预设发票信息模板中的位置标签；从与待查询企业对应的发票信息中，确定与位置标签对应的待提取位置；提取待提取位置的目标企业的信息。
在其中一个实施例中，图谱生成模块还用于将待查询企业作为基层目标企业；将所述基层目标企业以及得到的各层目标企业按照第一顺序进行排列，得到排列后的目标企业；根据排列后的目标企业，获取相邻层的目标企业之间的供销关系；根据排列后的目标企业以及相邻层的目标企业之间的供销关系，生成与待查询企业对应的企业供销关系图谱。
在其中一个实施例中，企业供销图谱生成装置还包括目标企业划分模块，用于图谱生成模块生成与待查询企业对应的企业供销关系图谱之后，将每个目标企业划分到不同的初始企业社群中，并获取与各个初始企业社群对应的模块度；模块度根据企业社群所对应的虚拟结构生成；将目标企业划分到与目标企业相邻的初始企业社群中，得到中间企业社群；获取中间企业社群的模块度，若模块度大于初始企业社群的模块度，则接受本次划分；将目标企业再次划分到与目标企业相邻的中间企业社群中，直到得到的企业社群的模块度达到对应的阈值；当得到的企业社群的模块度达到对应的阈值时，获取得到的企业社群，作 为目标企业社群。
在其中一个实施例中，企业供销关系图谱生成装置还包括等级获取模块，用于获取同一目标企业社群中的目标企业；识别目标企业的下层目标企业，获取下层目标企业的初始重要值以及目标企业与所述下层目标企业之间的交易次数；根据交易次数与权重的对应关系，确定与获取的交易次数对应的权重；根据下层目标企业的初始重要值和权重，得到下层目标企业的目标重要值；获取各个下层目标企业的目标重要值之和，作为目标企业的重要值，并确定与目标企业的重要值对应的重要等级。
在其中一个实施例中，企业供销关系图谱生成装置发票验证模块，用于获取目标企业在预设时间范围内的历史发票信息；根据历史发票信息，生成与目标企业对应的发票验证文件；根据发票验证文件，对目标企业的发票信息进行验证；若发票信息验证错误，则生成相应的预警消息，并将预警消息发送至对应的目标企业。
在其中一个实施例中，企业供销关系图谱生成装置还包括报告生成模块，用于提取生成的企业供销关系图谱中的目标企业；获取与各个目标企业对应的基本信息；将企业供销关系图谱和各个目标企业的基本信息，按照第二顺序加载到预设供销关系报告模板中，生成待查询企业的供销关系报告。
上述各个实施例，企业供销关系图谱生成装置实现了不断从企业的发票信息中提取目标企业，以获取企业的多层供销关系的目的，避免了传统方法中只能获取企业的单层供销关系的缺陷，保证了对企业的实际供销关系的全面了解，从而提高了获取的企业供销关系的准确度。
关于企业供销关系图谱生成装置的具体限定可以参见上文中对于企业供销关系图谱生成方法的限定，在此不再赘述。上述企业供销关系图谱生成装置中的各个模块可全部或部分通过软件、硬件及其组合来实现。上述各模块可以硬件形式内嵌于或独立于计算机设备中的处理器中，也可以以软件形式存储于计算机设备中的存储器中，以便于处理器调用执行以上各个模块对应的操作。
在其中一个实施例中，提供了一种计算机设备，该计算机设备可以是服务器，其内部结构图可以如图7所示。该计算机设备包括通过系统总线连接的处理器、存储器、网络接口和数据库。其中，该计算机设备的处理器用于提供计算和控制能力。该计算机设备的存储器包括非易失性计算机可读存储介质、内存储器。该非易失性计算机可读存储介质存储有操作系统、计算机可读指令和数据库。该内存储器为非易失性计算机可读存储介质中的操作系统和计算机可读指令的运行提供环境。该计算机设备的数据库用于存储发票信息。该计算机设备的网络接口用于与外部的终端通过网络连接通信。该计算机可读指令被处理器执行时以实现一种企业供销关系图谱生成方法。
本领域技术人员可以理解，图7中示出的结构，仅仅是与本申请方案相关的部分结构的框图，并不构成对本申请方案所应用于其上的计算机设备的限定，具体的计算机设备可以包括比图中所示更多或更少的部件，或者组合某些部件，或者具有不同的部件布置。
一种计算机设备，包括存储器和一个或多个处理器，存储器中储存有计算机可读指令，计算机可读指令被处理器执行时，使得一个或多个处理器执行以下步骤：
接收终端发送的查询请求，查询请求携带待查询企业的标识信息；
根据待查询企业的标识信息查询数据库，获取与待查询企业对应的发票信息；
从与待查询企业对应的发票信息中提取目标企业的信息；
获取目标企业的发票信息，从目标企业的发票信息中再次提取目标企业的信息；直到提取到的目标企业的层数满足设定条件；及
当提取到的目标企业的层数满足设定条件时，根据待查询企业以及得到的各层目标企业，生成与待查询企业对应的企业供销关系图谱。
在其中一个实施例中，处理器执行计算机可读指令时还实现以下步骤：获取预设发票信息模板；获取目标企业的信息在预设发票信息模板中的位置标签；从与待查询企业对应的发票信息中，确定与位置标签对应的待提取位置；及提取待提取位置的目标企业的信息。
在其中一个实施例中，处理器执行计算机可读指令时还实现以下步骤：将待查询企业作为基层目标企业；将基层目标企业以及得到的各层目标企业按照第一顺序进行排列，得到排列后的目标企业；根据排列后的目标企业，获取相邻层的目标企业之间的供销关系；及根据排列后的目标企业以及相邻层的目标企业之间的供销关系，生成与待查询企业对应的企业供销关系图谱。
在其中一个实施例中，处理器执行计算机可读指令时还实现以下步骤：在生成与待查询企业对应的企业供销关系图谱之后，将每个目标企业划分到不同的初始企业社群中，并获取与各个初始企业社群对应的模块度；模块度根据企业社群所对应的虚拟结构生成；将目标企业划分到与目标企业相邻的初始企业社群中，得到中间企业社群；获取中间企业社群的模块度，若模块度大于初始企业社群的模块度，则接受本次划分；将目标企业再次划分到与目标企业相邻的中间企业社群中，直到得到的企业社群的模块度达到对应的阈值；及当得到的企业社群的模块度达到对应的阈值时，获取得到的企业社群，作为目标企业社群。
在其中一个实施例中，处理器执行计算机可读指令时还实现以下步骤：获取同一目标企业社群中的目标企业；识别目标企业的下层目标企业，获取下层目标企业的初始重要值以及目标企业与下层目标企业之间的交易次数；根据交易次数与权重的对应关系，确定与获取的交易次数对应的权重；根据下层目标企业的初始重要值和所述权重，得到下层目标企业的目标重要值；及获取各个下层目标企业的目标重要值之和，作为目标企业的重要值，并确定与目标企业的重要值对应的重要等级。
在其中一个实施例中，处理器执行计算机可读指令时还实现以下步骤：获取目标企业在预设时间范围内的历史发票信息；根据历史发票信息，生成与目标企业对应的发票验证文件；根据发票验证文件，对目标企业的发票信息进行验证；及若发票信息验证错误，则生成相应的预警消息，并将预警消息发送至对应的目标企业。
在其中一个实施例中，处理器执行计算机可读指令时还实现以下步骤：提取生成的企业供销关系图谱中的目标企业；获取与各个目标企业对应的基本信息；及将企业供销关系图谱和各个目标企业的基本信息，按照第二顺序加载到预设供销关系报告模板中，生成待查询企业的供销关系报告。
上述各个实施例，计算机设备通过处理器上运行的计算机可读指令，实现了不断从企业的发票信息中提取目标企业，以获取企业的多层供销关系的目的，避免了传统方法中只能获取企业的单层供销关系的缺陷，保证了对企业的实际供销关系的全面了解，从而提高了获取的企业供销关系的准确度。
一个或多个存储有计算机可读指令的非易失性计算机可读存储介质，计算机可读指令被一个或多个处理器执行时，使得一个或多个处理器执行以下步骤：
接收终端发送的查询请求，查询请求携带待查询企业的标识信息；
根据待查询企业的标识信息查询数据库，获取与待查询企业对应的发票信息；
从与待查询企业对应的发票信息中提取目标企业的信息；
获取目标企业的发票信息，从目标企业的发票信息中再次提取目标企业的信息；直到提取到的目标企业的层数满足设定条件；及
当提取到的目标企业的层数满足设定条件时，根据待查询企业以及得到的各层目标企业，生成与待查询企业对应的企业供销关系图谱。
在其中一个实施例中，计算机可读指令被处理器执行时还实现以下步骤：获取预设发票信息模板；获取目标企业的信息在预设发票信息模板中的位置标签；从与待查询企业对应的发票信息中，确定与位置标签对应的待提取位置；及提取待提取位置的目标企业的信息。
在其中一个实施例中，计算机可读指令被处理器执行时还实现以下步骤：将待查询企业作为基层目标企业；将基层目标企业以及得到的各层目标企业按照第一顺序进行排列，得到排列后的目标企业；根据排列后的目标企业，获取相邻层的目标企业之间的供销关系；及根据排列后的目标企业以及相邻层的目标企业之间的供销关系，生成与待查询企业对应的企业供销关系图谱。
在其中一个实施例中，计算机可读指令被处理器执行时还实现以下步骤：在生成与待查询企业对应的企业供销关系图谱之后，将每个目标企业划分到不同的初始企业社群中，并获取与各个初始企业社群对应的模块度；模块度根据企业社群所对应的虚拟结构生成；将目标企业划分到与目标企业相邻的初始企业社群中，得到中间企业社群；获取中间企业社群的模块度，若模块度大于初始企业社群的模块度，则接受本次划分；将目标企业再次划分到与目标企业相邻的中间企业社群中，直到得到的企业社群的模块度达到对应的阈值；及当得到的企业社群的模块度达到对应的阈值时，获取得到的企业社群，作为目标企业社群。
在其中一个实施例中，计算机可读指令被处理器执行时还实现以下步骤：获取同一目 标企业社群中的目标企业；识别目标企业的下层目标企业，获取下层目标企业的初始重要值以及目标企业与下层目标企业之间的交易次数；根据交易次数与权重的对应关系，确定与获取的交易次数对应的权重；根据下层目标企业的初始重要值和权重，得到下层目标企业的目标重要值；及获取各个下层目标企业的目标重要值之和，作为目标企业的重要值，并确定与目标企业的重要值对应的重要等级。
在其中一个实施例中，计算机可读指令被处理器执行时还实现以下步骤：获取目标企业在预设时间范围内的历史发票信息；根据历史发票信息，生成与目标企业对应的发票验证文件；根据发票验证文件，对目标企业的发票信息进行验证；及若发票信息验证错误，则生成相应的预警消息，并将预警消息发送至对应的目标企业。
在其中一个实施例中，计算机可读指令被处理器执行时还实现以下步骤：提取生成的企业供销关系图谱中的目标企业；获取与各个目标企业对应的基本信息；及将企业供销关系图谱和各个目标企业的基本信息，按照第二顺序加载到预设供销关系报告模板中，生成待查询企业的供销关系报告。
上述各个实施例，非易失性计算机可读存储介质通过其存储的计算机可读指令，实现了不断从企业的发票信息中提取目标企业，以获取企业的多层供销关系的目的，避免了传统方法中只能获取企业的单层供销关系的缺陷，保证了对企业的实际供销关系的全面了解，从而提高了获取的企业供销关系的准确度。
本领域普通技术人员可以理解实现上述实施例方法中的全部或部分流程，是可以通过计算机可读指令来指令相关的硬件来完成，所述的计算机可读指令可存储于一非易失性计算机可读存储介质中，该计算机可读指令在执行时，可包括如上述各方法的实施例的流程。其中，本申请所提供的各实施例中所使用的对存储器、存储、数据库或其它介质的任何引用，均可包括非易失性和/或易失性存储器。非易失性存储器可包括只读存储器(ROM)、可编程ROM(PROM)、电可编程ROM(EPROM)、电可擦除可编程ROM(EEPROM)或闪存。易失性存储器可包括随机存取存储器(RAM)或者外部高速缓冲存储器。作为说明而非局限，RAM以多种形式可得，诸如静态RAM(SRAM)、动态RAM(DRAM)、同步DRAM(SDRAM)、双数据率SDRAM(DDRSDRAM)、增强型SDRAM(ESDRAM)、同步链路(Synchlink)DRAM(SLDRAM)、存储器总线(Rambus)直接RAM(RDRAM)、直接存储器总线动态RAM(DRDRAM)、以及存储器总线动态RAM(RDRAM)等。
以上实施例的各技术特征可以进行任意的组合，为使描述简洁，未对上述实施例中的各个技术特征所有可能的组合都进行描述，然而，只要这些技术特征的组合不存在矛盾，都应当认为是本说明书记载的范围。
以上所述实施例仅表达了本申请的几种实施方式，其描述较为具体和详细，但并不能因此而理解为对发明专利范围的限制。应当指出的是，对于本领域的普通技术人员来说，在不脱离本申请构思的前提下，还可以做出若干变形和改进，这些都属于本申请的保护范围。因此，本申请专利的保护范围应以所附权利要求为准。

Claims (20)

  1. 一种企业供销关系图谱生成方法，包括：
    接收终端发送的查询请求，所述查询请求携带待查询企业的标识信息；
    根据所述待查询企业的标识信息查询数据库，获取与所述待查询企业对应的发票信息；
    从与所述待查询企业对应的发票信息中提取目标企业的信息；
    获取所述目标企业的发票信息，从所述目标企业的发票信息中再次提取目标企业的信息；直到提取到的目标企业的层数满足设定条件；及
    当提取到的目标企业的层数满足设定条件时，根据所述待查询企业以及得到的各层目标企业，生成与所述待查询企业对应的企业供销关系图谱。
  2. 根据权利要求1所述的方法，其特征在于，所述从与所述待查询企业对应的发票信息中提取目标企业的信息，包括：
    获取预设发票信息模板；
    获取目标企业的信息在所述预设发票信息模板中的位置标签；
    从与所述待查询企业对应的发票信息中，确定与所述位置标签对应的待提取位置；及
    提取所述待提取位置的目标企业的信息。
  3. 根据权利要求1所述的方法，其特征在于，所述根据所述待查询企业以及得到的各层目标企业，生成与所述待查询企业对应的企业供销关系图谱，包括：
    将所述待查询企业作为基层目标企业；
    将所述基层目标企业以及得到的各层目标企业按照第一顺序进行排列，得到排列后的目标企业；
    根据所述排列后的目标企业，获取相邻层的目标企业之间的供销关系；及
    根据所述排列后的目标企业以及相邻层的目标企业之间的供销关系，生成与所述待查询企业对应的企业供销关系图谱。
  4. 根据权利要求1至3任意一项所述的方法，其特征在于，在生成与所述待查询企业对应的企业供销关系图谱之后，所述方法还包括：
    将每个目标企业划分到不同的初始企业社群中，并获取与各个所述初始企业社群对应的模块度；所述模块度根据企业社群所对应的虚拟结构生成；
    将目标企业划分到与所述目标企业相邻的初始企业社群中，得到中间企业社群；
    获取所述中间企业社群的模块度，若所述模块度大于所述初始企业社群的模块度，则接受本次划分；
    将目标企业再次划分到与所述目标企业相邻的中间企业社群中，直到得到的企业社群的模块度达到对应的阈值；及
    当得到的企业社群的模块度达到对应的阈值时，获取所述得到的企业社群，作为目标企业社群。
  5. 根据权利要求4所述的方法，其特征在于，还包括：
    获取同一目标企业社群中的目标企业；
    识别所述目标企业的下层目标企业，获取所述下层目标企业的初始重要值以及所述目标企业与所述下层目标企业之间的交易次数；
    根据交易次数与权重的对应关系，确定与所述获取的交易次数对应的权重；
    根据所述下层目标企业的初始重要值和所述权重，得到所述下层目标企业的目标重要值；及
    获取各个所述下层目标企业的目标重要值之和，作为所述目标企业的重要值，并确定与所述目标企业的重要值对应的重要等级。
  6. 根据权利要求4所述的方法，其特征在于，还包括：
    获取目标企业在预设时间范围内的历史发票信息；
    根据所述历史发票信息，生成与所述目标企业对应的发票验证文件；
    根据所述发票验证文件，对所述目标企业的发票信息进行验证；及
    若发票信息验证错误，则生成相应的预警消息，并将所述预警消息发送至对应的目标企业。
  7. 根据权利要求4所述的方法，其特征在于，还包括：
    提取所述生成的企业供销关系图谱中的目标企业；
    获取与各个所述目标企业对应的基本信息；及
    将所述企业供销关系图谱和各个目标企业的基本信息，按照第二顺序加载到预设供销关系报告模板中，生成所述待查询企业的供销关系报告。
  8. 一种企业供销关系图谱生成装置，包括：
    请求接收模块，用于接收终端发送的查询请求，所述查询请求携带待查询企业的标识信息；
    信息查询模块，用于根据所述待查询企业的标识信息查询数据库，获取与所述待查询企业对应的发票信息；
    第一信息提取模块，用于从与所述待查询企业对应的发票信息中提取目标企业的信息；
    第二信息提取模块，用于获取所述目标企业的发票信息，从所述目标企业的发票信息中再次提取目标企业的信息；直到提取到的目标企业的层数满足设定条件；及
    图谱生成模块，用于当提取到的目标企业的层数满足设定条件时，根据所述待查询企业以及得到的各层目标企业，生成与所述待查询企业对应的企业供销关系图谱。
  9. 根据权利要求8所述的装置，其特征在于，所述第一信息提取模块还用于获取预设发票信息模板；获取目标企业的信息在所述预设发票信息模板中的位置标签；从与所述待查询企业对应的发票信息中，确定与所述位置标签对应的待提取位置；提取所述待提取位置的目标企业的信息。
  10. 根据权利要求8所述的装置，其特征在于，所述图谱生成模块还用于将所述待查询企业作为基层目标企业；将所述基层目标企业以及得到的各层目标企业按照第一顺序进 行排列，得到排列后的目标企业；根据所述排列后的目标企业，获取相邻层的目标企业之间的供销关系；根据所述排列后的目标企业以及相邻层的目标企业之间的供销关系，生成与所述待查询企业对应的企业供销关系图谱。
  11. 一种计算机设备，包括存储器及一个或多个处理器，所述存储器中储存有计算机可读指令，所述计算机可读指令被所述一个或多个处理器执行时，使得所述一个或多个处理器执行以下步骤：
    接收终端发送的查询请求，所述查询请求携带待查询企业的标识信息；
    根据所述待查询企业的标识信息查询数据库，获取与所述待查询企业对应的发票信息；
    从与所述待查询企业对应的发票信息中提取目标企业的信息；
    获取所述目标企业的发票信息，从所述目标企业的发票信息中再次提取目标企业的信息；直到提取到的目标企业的层数满足设定条件；及
    当提取到的目标企业的层数满足设定条件时，根据所述待查询企业以及得到的各层目标企业，生成与所述待查询企业对应的企业供销关系图谱。
  12. 根据权利要求11所述的计算机设备，其特征在于，所述处理器执行所述计算机可读指令时还执行以下步骤：
    获取预设发票信息模板；
    获取目标企业的信息在所述预设发票信息模板中的位置标签；
    从与所述待查询企业对应的发票信息中，确定与所述位置标签对应的待提取位置；及
    提取所述待提取位置的目标企业的信息。
  13. 根据权利要求11所述的计算机设备，其特征在于，所述处理器执行所述计算机可读指令时还执行以下步骤：
    将所述待查询企业作为基层目标企业；
    将所述基层目标企业以及得到的各层目标企业按照第一顺序进行排列，得到排列后的目标企业；
    根据所述排列后的目标企业，获取相邻层的目标企业之间的供销关系；及
    根据所述排列后的目标企业以及相邻层的目标企业之间的供销关系，生成与所述待查询企业对应的企业供销关系图谱。
  14. 根据权利要求11至13任意一项所述的计算机设备，其特征在于，所述处理器执行所述计算机可读指令时还执行以下步骤：
    将每个目标企业划分到不同的初始企业社群中，并获取与各个所述初始企业社群对应的模块度；所述模块度根据企业社群所对应的虚拟结构生成；
    将目标企业划分到与所述目标企业相邻的初始企业社群中，得到中间企业社群；
    获取所述中间企业社群的模块度，若所述模块度大于所述初始企业社群的模块度，则接受本次划分；
    将目标企业再次划分到与所述目标企业相邻的中间企业社群中，直到得到的企业社群 的模块度达到对应的阈值；及
    当得到的企业社群的模块度达到对应的阈值时，获取所述得到的企业社群，作为目标企业社群。
  15. 根据权利要求14所述的计算机设备，其特征在于，所述处理器执行所述计算机可读指令时还执行以下步骤：
    获取同一目标企业社群中的目标企业；
    识别所述目标企业的下层目标企业，获取所述下层目标企业的初始重要值以及所述目标企业与所述下层目标企业之间的交易次数；
    根据交易次数与权重的对应关系，确定与所述获取的交易次数对应的权重；
    根据所述下层目标企业的初始重要值和所述权重，得到所述下层目标企业的目标重要值；及
    获取各个所述下层目标企业的目标重要值之和，作为所述目标企业的重要值，并确定与所述目标企业的重要值对应的重要等级。
  16. 一个或多个存储有计算机可读指令的非易失性计算机可读存储介质，所述计算机可读指令被一个或多个处理器执行时，使得所述一个或多个处理器执行以下步骤：接收终端发送的查询请求，所述查询请求携带待查询企业的标识信息；
    根据所述待查询企业的标识信息查询数据库，获取与所述待查询企业对应的发票信息；
    从与所述待查询企业对应的发票信息中提取目标企业的信息；
    获取所述目标企业的发票信息，从所述目标企业的发票信息中再次提取目标企业的信息；直到提取到的目标企业的层数满足设定条件；及
    当提取到的目标企业的层数满足设定条件时，根据所述待查询企业以及得到的各层目标企业，生成与所述待查询企业对应的企业供销关系图谱。
  17. 根据权利要求16所述的存储介质，其特征在于，所述计算机可读指令被所述处理器执行时还执行以下步骤：
    获取预设发票信息模板；
    获取目标企业的信息在所述预设发票信息模板中的位置标签；
    从与所述待查询企业对应的发票信息中，确定与所述位置标签对应的待提取位置；及
    提取所述待提取位置的目标企业的信息。
  18. 根据权利要求16所述的存储介质，其特征在于，所述计算机可读指令被所述处理器执行时还执行以下步骤：
    将所述待查询企业作为基层目标企业；
    将所述基层目标企业以及得到的各层目标企业按照第一顺序进行排列，得到排列后的目标企业；
    根据所述排列后的目标企业，获取相邻层的目标企业之间的供销关系；及
    根据所述排列后的目标企业以及相邻层的目标企业之间的供销关系，生成与所述待查 询企业对应的企业供销关系图谱。
  19. 根据权利要求16至18任意一项所述的存储介质，其特征在于，所述计算机可读指令被所述处理器执行时还执行以下步骤：
    将每个目标企业划分到不同的初始企业社群中，并获取与各个所述初始企业社群对应的模块度；所述模块度根据企业社群所对应的虚拟结构生成；
    将目标企业划分到与所述目标企业相邻的初始企业社群中，得到中间企业社群；
    获取所述中间企业社群的模块度，若所述模块度大于所述初始企业社群的模块度，则接受本次划分；
    将目标企业再次划分到与所述目标企业相邻的中间企业社群中，直到得到的企业社群的模块度达到对应的阈值；及
    当得到的企业社群的模块度达到对应的阈值时，获取所述得到的企业社群，作为目标企业社群。
  20. 根据权利要求19所述的存储介质，其特征在于，所述计算机可读指令被所述处理器执行时还执行以下步骤：
    获取同一目标企业社群中的目标企业；
    识别所述目标企业的下层目标企业，获取所述下层目标企业的初始重要值以及所述目标企业与所述下层目标企业之间的交易次数；
    根据交易次数与权重的对应关系，确定与所述获取的交易次数对应的权重；
    根据所述下层目标企业的初始重要值和所述权重，得到所述下层目标企业的目标重要值；及
    获取各个所述下层目标企业的目标重要值之和，作为所述目标企业的重要值，并确定与所述目标企业的重要值对应的重要等级。
PCT/CN2018/125457 2018-10-17 2018-12-29 企业供销关系图谱生成方法、装置和计算机设备 Ceased WO2020077876A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201811210744.0 2018-10-17
CN201811210744.0A CN109543073A (zh) 2018-10-17 2018-10-17 企业供销关系图谱生成方法、装置和计算机设备

Publications (1)

Publication Number Publication Date
WO2020077876A1 true WO2020077876A1 (zh) 2020-04-23

Family

ID=65844404

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/125457 Ceased WO2020077876A1 (zh) 2018-10-17 2018-12-29 企业供销关系图谱生成方法、装置和计算机设备

Country Status (2)

Country Link
CN (1) CN109543073A (zh)
WO (1) WO2020077876A1 (zh)

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110389966B (zh) * 2019-06-28 2022-07-12 苏州浪潮智能科技有限公司 一种信息处理方法及装置
CN110309154B (zh) * 2019-06-28 2021-06-29 京东数字科技控股有限公司 基于图谱的实体特征选择方法、装置、设备和存储介质
CN112232894B (zh) * 2020-10-27 2024-09-27 江苏税软软件科技有限公司 基于增值税发票的数据分析方法
CN112529664B (zh) * 2020-12-15 2024-08-20 航天信息股份有限公司 进销商品比对方法、装置、存储介质及电子设备
CN115599965B (zh) * 2022-12-13 2023-08-11 山东中慧强企信息科技有限公司 一种数据经济信息化管理系统

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105468592A (zh) * 2014-08-04 2016-04-06 北京奇虎科技有限公司 一种关联数据表的展示方法和装置
CN106355488A (zh) * 2016-09-28 2017-01-25 深圳市喜悦智慧数据有限公司 一种基于征信的税控方法及系统
CN106682180A (zh) * 2016-12-29 2017-05-17 广州华多网络科技有限公司 数据查询方法及装置
CN108268799A (zh) * 2017-12-28 2018-07-10 上海数据交易中心有限公司 数据查询系统和方法、存储介质、终端
CN108334625A (zh) * 2018-02-09 2018-07-27 深圳壹账通智能科技有限公司 用户信息的处理方法、装置、计算机设备和存储介质

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106779996A (zh) * 2016-12-08 2017-05-31 深圳微众税银信息服务有限公司 一种供应链金融中企业数据挖掘方法及系统
CN107527151A (zh) * 2017-08-31 2017-12-29 郑州云海信息技术有限公司 一种构建企业画像的方法及系统
CN108664582B (zh) * 2018-05-04 2021-06-18 企查查科技有限公司 企业关系的查询方法、装置、计算机设备及存储介质

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105468592A (zh) * 2014-08-04 2016-04-06 北京奇虎科技有限公司 一种关联数据表的展示方法和装置
CN106355488A (zh) * 2016-09-28 2017-01-25 深圳市喜悦智慧数据有限公司 一种基于征信的税控方法及系统
CN106682180A (zh) * 2016-12-29 2017-05-17 广州华多网络科技有限公司 数据查询方法及装置
CN108268799A (zh) * 2017-12-28 2018-07-10 上海数据交易中心有限公司 数据查询系统和方法、存储介质、终端
CN108334625A (zh) * 2018-02-09 2018-07-27 深圳壹账通智能科技有限公司 用户信息的处理方法、装置、计算机设备和存储介质

Also Published As

Publication number Publication date
CN109543073A (zh) 2019-03-29

Similar Documents

Publication Publication Date Title
WO2020077876A1 (zh) 企业供销关系图谱生成方法、装置和计算机设备
US12277244B2 (en) Data aggregation system for enabling query operations on restricted data that originates from multiple independent multiple sources
WO2021004333A1 (zh) 基于知识图谱的事件处理方法、装置、设备和存储介质
WO2020186786A1 (zh) 文件处理方法、装置、计算机设备和存储介质
WO2019109918A1 (zh) 摘要文本生成方法、计算机可读存储介质和计算机设备
WO2021164205A1 (zh) 基于身份识别的数据审核方法、装置和计算机设备
CN111061859A (zh) 基于知识图谱的数据处理方法、装置和计算机设备
US10311364B2 (en) Predictive intelligence for service and support
CN110135943B (zh) 产品推荐方法、装置、计算机设备和存储介质
CN110609954A (zh) 数据获取方法、装置、计算机设备和存储介质
CN108334625B (zh) 用户信息的处理方法、装置、计算机设备和存储介质
US20190073599A1 (en) Systems and methods for expediting rule-based data processing
CN106560853A (zh) 一种业务处理方法和装置
CN112286934A (zh) 数据库表导入方法、装置、设备及介质
CN111414427B (zh) 一种适用于准实时服务的数据处理方法及装置
CN111476595A (zh) 产品推送方法、装置、计算机设备和存储介质
CN109669951B (zh) 对象查询方法、装置、计算机设备和存储介质
CN111047336A (zh) 用户标签推送、用户标签展示方法、装置和计算机设备
CN112463783A (zh) 索引数据监控方法、装置、计算机设备和存储介质
CN111522842A (zh) 一种etl数据处理方法、装置、计算机设备和存储介质
US20190294594A1 (en) Identity Data Enhancement
WO2019019753A1 (zh) 提供健康报告的判断方法、装置、计算机设备和存储介质
CN116861087B (zh) 基于大语言模型的客户智能推荐方法、系统、设备及介质
US20250036691A1 (en) Method and system for managing computer aided design (cad) documents
CN114511379B (zh) 商品异常预测模型训练、商品推荐方法、装置及设备

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 18936940

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 06/08/2021)

122 Ep: pct application non-entry in european phase

Ref document number: 18936940

Country of ref document: EP

Kind code of ref document: A1