Enterprise information query method and device and server

Abstract

The invention provides an enterprise information query method and device and a server, and relates to the technical field of information query, and the method comprises the steps: obtaining enterprise query information of a user side; performing data analysis processing on the enterprise query information by using a deep learning analysis model and a preset attribute keyword table, determining target query information, and generating an SQL statement according to the target query information, the target query information being information corresponding to the attribute keyword table in the enterprise query information; and matching the SQL statement with a preset database, determining target enterprise information, and sending the target enterprise information to the user side. According to the method, the accuracy of enterprise information query can be remarkably improved while the user experience is improved based on a deep learning algorithm.

Description

Technical Field

[0001] The present invention relates to the technical field of information query, and in particular to an enterprise information query method, device and server. Background Art

[0002] When users use enterprise search tools, many users are stuck in a dilemma due to lack of experience or lack of clear understanding of the enterprises they want to search. At present, relevant technologies have proposed that a large number of filtering conditions can be set to allow users to choose by themselves to help users filter out the enterprises they want to search. However, when there are fewer filtering conditions, the query accuracy is poor and the help to users is limited. When there are more filtering conditions, it will increase the learning cost. Users need to learn these filtering conditions first before they can use the search system proficiently, which increases the difficulty for users. Summary of the invention

[0003] In view of this, the purpose of the present invention is to provide an enterprise information query method, device and server, which can significantly improve the accuracy of enterprise information query while improving user experience based on a deep learning algorithm.

[0004] In the first aspect, an embodiment of the present invention provides an enterprise information query method, which is applied to a large-scale search model, and the method includes: obtaining enterprise query information from a user end; using a deep learning analysis model and a preset attribute keyword table to perform data analysis and processing on the enterprise query information, determine target query information, and generate an SQL statement based on the target query information, wherein the target query information is information in the enterprise query information corresponding to the attribute keyword table; matching the SQL statement with a preset database, determining the target enterprise information, and sending the target enterprise information to the user end.

[0005] In one embodiment, before the step of obtaining enterprise query information from the user side, it includes: obtaining user input information and determining the query target of the user input information through a deep learning analysis model; determining the input information category based on the query target and the user identity information corresponding to the user input information through preset screening conditions.

[0006] In one embodiment, by presetting screening conditions, based on the query target and the user address corresponding to the user input information, the step of determining the category of the input information includes: when the query target is enterprise screening and the user identity information is a Chinese user, determining that the user input information is enterprise query information; when the query target is non-enterprise screening, or the user identity information is a non-Chinese user, determining that the user input information is chat information, and terminating the information query process.

[0007] In one embodiment, a deep learning analysis model and a preset attribute keyword table are used to perform data analysis and processing on enterprise query information to determine the target query information, including: extracting key attribute information in the enterprise query information according to the preset attribute keyword table; performing data analysis and processing on the key attribute information through a deep learning analysis model to determine the target query information.

[0008] In one embodiment, the step of extracting key attribute information from enterprise query information according to a preset attribute keyword table includes: extracting keywords from the enterprise query information in descending order of priority according to the priority of each attribute keyword in the preset attribute keyword table to determine the key attribute information.

[0009] In one embodiment, the method includes: when there is no content matching the preset attribute keyword table in the enterprise query information, sending a query failure notification to the user terminal.

[0010] In one embodiment, after performing data analysis on attribute keywords through a deep learning analysis model to determine the target query information, it includes: filtering invalid information on the target query information, and determining an SQL statement based on the filtered target query information, wherein the invalid information includes: information containing special fields.

[0011] In the second aspect, an embodiment of the present invention also provides an enterprise information query device, which is applied to a large-scale search model, and the device includes: an information acquisition module, which acquires enterprise query information from a user terminal; an information analysis module, which uses a deep learning analysis model and a preset attribute keyword table to perform data analysis and processing on the enterprise query information, determine target query information, and generate an SQL statement based on the target query information, wherein the target query information is information in the enterprise query information corresponding to the attribute keyword table; an information query module, which matches the SQL statement with a preset database, determines the target enterprise information, and sends the target enterprise information to the user terminal.

[0012] In a third aspect, an embodiment of the present invention further provides a server, comprising a processor and a memory, wherein the memory stores computer executable instructions that can be executed by the processor, and the processor executes the computer executable instructions to implement any one of the methods provided in the first aspect.

[0013] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, which stores computer-executable instructions. When the computer-executable instructions are called and executed by a processor, the computer-executable instructions prompt the processor to implement any one of the methods provided in the first aspect.

[0014] The embodiments of the present invention bring the following beneficial effects:

[0015] An enterprise information query method, device and server provided by an embodiment of the present invention, after obtaining the enterprise query information from the user end, uses a deep learning analysis model and a preset attribute keyword table to perform data analysis and processing on the enterprise query information, determines the target query information, and generates an SQL statement based on the target query information, wherein the target query information is the information in the enterprise query information corresponding to the attribute keyword table, matches the SQL statement with a preset database, determines the target enterprise information, and sends the target enterprise information to the user end. The embodiment of the present invention can be based on a deep learning algorithm, while improving the user experience, significantly improving the accuracy of enterprise information query.

[0016] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention are realized and obtained by the structures particularly pointed out in the description, claims and drawings.

[0017] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0019] Figure 1 A flowchart of a method for querying enterprise information provided by an embodiment of the present invention;

[0020] Figure 2 A schematic diagram of a user querying target enterprise information provided by an embodiment of the present invention;

[0021] Figure 3 A schematic diagram of the structure of an enterprise information query device provided by an embodiment of the present invention;

[0022] Figure 4 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0023] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution of the present invention will be clearly and completely described in combination with the embodiments below. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0024] At present, when users use enterprise search tools such as Tianyancha or Qichacha, many users are stuck in a dilemma due to lack of experience or lack of clear understanding of the enterprises they need to query. At present, relevant technologies propose that a large number of filtering conditions can be set to allow users to choose by themselves to help users filter out the enterprises they want to query. However, when there are fewer filtering conditions, the query accuracy of this solution is poor and the help to users is limited. When there are more filtering conditions, it will increase the huge learning cost, so that users need to learn these filtering conditions first before they can use the search system proficiently, thereby increasing the difficulty for users. Based on this, the enterprise information query method provided by the implementation of the present invention can help determine the user's true intention based on a deep learning algorithm, and significantly improve the accuracy and efficiency of enterprise information query while improving the user experience.

[0025] See also Figure 1 The flowchart of a method for querying enterprise information is shown in FIG. 1 . The method is applied to a large search model and mainly includes the following steps S102 to S106:

[0026] Step S102, obtaining enterprise query information from the user side, wherein the enterprise query information is user input information that meets the large-scale model query standard obtained through preset screening conditions. In one embodiment, before the step of obtaining the enterprise query information from the user side, the user input information is obtained, and the query target of the user input information is determined through a deep learning analysis model. The input information category is determined based on the query target and the user identity information corresponding to the user input information through preset screening conditions, wherein the preset screening conditions may include: 1. The large-scale search model is an enterprise information service model; 2. The input information from the user side is only used to screen enterprises; 3. Information query services are only provided to Chinese users; 4. The results fed back to the user side need to be given in conjunction with the database and cannot be fabricated.

[0027] In one embodiment, when the query target is enterprise screening and the user identity information is a Chinese user, the user input information is determined to be enterprise query information; when the query target is non-enterprise screening, or the user identity information is a non-Chinese user, the user input information is determined to be chat information, and the information query process is terminated. In another embodiment, when it is determined that the user input information is chat information, a database of feedback templates can be established based on actual usage, and special feedback processing can be performed for chat users.

[0028] Step S104, using the deep learning analysis model and the preset attribute keyword table, perform data analysis and processing on the enterprise query information, determine the target query information, and generate an SQL statement based on the target query information, wherein the target query information is the information in the enterprise query information corresponding to the attribute keyword table. In one embodiment, the process of performing data analysis and processing on the enterprise query information using the deep learning analysis model and the preset attribute keyword table is different from the prior art of matching the keywords in the enterprise query information to obtain the corresponding query results, nor is it by labeling the company information for label matching. Instead, it is directly based on the deep learning language to think about the user's input (enterprise query information), and generate an SQL statement based on the thinking result for query, breaking through the limitations of the traditional search system, and directly analyzing the user's intention based on the deep learning language, so as to adapt to various types of user queries.

[0029] Step S106, matches the SQL statement with the preset database, determines the target enterprise information, and sends the target enterprise information to the user end, wherein the SQL statement is a standardized statement used for query, and the generated SQL statement contains enterprise attributes. In one embodiment, the user input content, including the part of enterprise attributes (such as enterprise name, business scope, main products), is converted into an SQL statement and sent to the database, so that a query can be performed in the database to obtain the query result corresponding to this part of the content and feedback it to the user.

[0030] The above-mentioned enterprise information query method provided by the embodiment of the present invention can be based on a deep learning algorithm, which can significantly improve the accuracy of enterprise information query while improving the user experience.

[0031] The embodiment of the present invention also provides an implementation method for determining target enterprise information based on enterprise query information of the user end, and the details are as follows (1) to (3):

[0032] (1) Extract key attribute information from the enterprise query information according to a preset attribute keyword table. In one implementation, according to the priority of each attribute keyword in the preset attribute keyword table, the enterprise query information is sequentially extracted in descending order of priority to determine key attribute information (e.g., attribute keywords include enterprise name, business scope, and main products, with main products being the first priority, and enterprise name and business scope both being the second priority). In one implementation, see Figure 2 The schematic diagram of a user querying target enterprise information is shown in FIG. The enterprise query information on the user side can be divided into two types. One is the enterprise that the user clearly wants to query (for example, I need an enterprise that produces furniture), and the other is that the user is not sure about the enterprise to be queried, but is clear about the products, services or labor that he can provide, and hopes that the system will recommend an enterprise or organization ( Figure 2 In China, there are companies that deal in bulk cement. Please recommend some companies. In Shanghai, there are institutions that provide English training for children).

[0033] (2) The key attribute information is analyzed and processed by the deep learning analysis model to determine the target query information. In one embodiment, the enterprise query information can be matched with attribute keywords first, and then deep learning can be performed to determine the target query information. Alternatively, the enterprise query information can be analyzed and processed according to the deep learning analysis model first to determine the model thinking result, and the model thinking result is matched with the preset attribute keyword table to determine the key attribute information. In actual application, when the user inputs "I need a company that produces furniture", the model thinks about this piece of enterprise query information and obtains the model thinking result "the user needs a company that produces furniture". The model thinking result is matched with the attribute keyword "company name" in the preset attribute keyword table to determine the key attribute information as "furniture", and the furniture is written as an SQL statement, and the SQL statement is matched with the preset database to determine the target enterprise information.

[0034] (3) When there is no content matching the preset attribute keyword table in the enterprise query information, a query failure notification is sent to the user terminal. When there is content matching the preset attribute keyword table in the enterprise query information, the target query information is filtered for invalid information, and an SQL statement is determined based on the filtered target query information, and the SQL statement is matched with the preset database to determine the target enterprise information, and the target enterprise information is sent to the user terminal, wherein the invalid information includes: information containing special fields. In one embodiment, when sending a query failure notification to the user terminal, a search template or search format adjustment suggestion can be sent to the user terminal at the same time, and the adjusted enterprise query information can be re-acquired.

[0035] To sum up, the present invention can break through the limitations of traditional search systems, use large models and deep learning analysis models to realize auxiliary analysis of user intentions, build a search system from scratch, and enable the search system to have excellent expressive and generalization capabilities, which can adapt to various types of user queries.

[0036] For the enterprise information query method provided in the above embodiment, the embodiment of the present invention provides an enterprise information query device, which is applied to a large search model, see Figure 3 The structure diagram of a corporate information query device shown in FIG. 1 includes the following parts:

[0037] Information acquisition module 302, acquiring enterprise query information from the user end;

[0038] The information analysis module 304 uses the deep learning analysis model and the preset attribute keyword table to perform data analysis and processing on the enterprise query information, determine the target query information, and generate an SQL statement according to the target query information, wherein the target query information is the information in the enterprise query information corresponding to the attribute keyword table;

[0039] The information query module 306 matches the SQL statement with the preset database, determines the target enterprise information, and sends the target enterprise information to the user end.

[0040] The above-mentioned data processing device provided in the embodiment of the present application can be based on a deep learning algorithm to significantly improve the accuracy of enterprise information query while improving user experience.

[0041] In one embodiment, before performing the step of obtaining enterprise query information from the user side, the above-mentioned information acquisition module 302 is also used to: obtain user input information, and determine the query target of the user input information through a deep learning analysis model; through preset screening conditions, determine the input information category based on the query target and the user identity information corresponding to the user input information.

[0042] In one embodiment, when performing the step of determining the input information category based on the query target and the user address corresponding to the user input information through preset screening conditions, the above-mentioned information acquisition module 302 is also used to: when the query target is enterprise screening and the user identity information is a Chinese user, determine that the user input information is enterprise query information; when the query target is non-enterprise screening, or the user identity information is a non-Chinese user, determine that the user input information is chat information, and terminate the information query process.

[0043] In one embodiment, when performing data analysis and processing on enterprise query information using a deep learning analysis model and a preset attribute keyword table to determine target query information, the above-mentioned information analysis module 304 is also used to: extract key attribute information in the enterprise query information according to the preset attribute keyword table; perform data analysis and processing on the key attribute information through a deep learning analysis model to determine the target query information.

[0044] In one embodiment, when performing the step of extracting key attribute information in the enterprise query information according to a preset attribute keyword table, the above-mentioned information analysis module 304 is also used to: extract keywords from the enterprise query information in order from high to low priority according to the priority of each attribute keyword in the preset attribute keyword table to determine the key attribute information.

[0045] In one implementation, the information analysis module 304 is further configured to send a query failure notification to the user terminal when there is no content matching the preset attribute keyword table in the enterprise query information.

[0046] In one embodiment, after performing data analysis on attribute keywords through a deep learning analysis model to determine target query information, the above-mentioned information analysis module 304 is also used to: filter invalid information from the target query information, and determine the SQL statement based on the filtered target query information, wherein the invalid information includes: information containing special fields.

[0047] The device provided in the embodiment of the present invention has the same implementation principle and technical effects as those of the aforementioned method embodiment. For the sake of brief description, for matters not mentioned in the device embodiment, reference may be made to the corresponding contents in the aforementioned method embodiment.

[0048] An embodiment of the present invention provides an electronic device. Specifically, the electronic device includes a processor and a storage device. The storage device stores a computer program, and when the computer program is executed by the processor, it executes the method described in any one of the above-mentioned implementation methods.

[0049] Figure 4 A structural diagram of an electronic device provided in an embodiment of the present invention, the electronic device 100 includes: a processor 40, a memory 41, a bus 42 and a communication interface 43, wherein the processor 40, the communication interface 43 and the memory 41 are connected via the bus 42; the processor 40 is used to execute an executable module stored in the memory 41, such as a computer program.

[0050] The memory 41 may include a high-speed random access memory (RAM), and may also include a non-volatile memory, such as at least one disk memory. The communication connection between the system network element and at least one other network element is realized through at least one communication interface 43 (which may be wired or wireless), and the Internet, wide area network, local area network, metropolitan area network, etc. may be used.

[0051] The bus 42 may be an ISA bus, a PCI bus, or an EISA bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 4 Only one bidirectional arrow is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0052] Among them, the memory 41 is used to store programs, and the processor 40 executes the program after receiving the execution instruction. The method executed by the device for flow process definition disclosed in any embodiment of the above-mentioned embodiment of the present invention can be applied to the processor 40 or implemented by the processor 40.

[0053] The processor 40 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the hardware integrated logic circuit or software instructions in the processor 40. The above processor 40 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present invention can be implemented or executed. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor. The steps of the method disclosed in the embodiments of the present invention can be directly embodied as a hardware decoding processor to execute, or can be executed by a combination of hardware and software modules in the decoding processor. The software module can be located in a mature storage medium in the field such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory 41, and the processor 40 reads the information in the memory 41 and completes the steps of the above method in combination with its hardware.

[0054] The computer program product of the readable storage medium provided in the embodiment of the present invention includes a computer-readable storage medium storing program code, and the instructions included in the program code can be used to execute the methods described in the previous method embodiments. The specific implementation can be referred to the previous method embodiments, which will not be repeated here.

[0055] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program codes.

[0056] Finally, it should be noted that the above-described embodiments are only specific implementations of the present invention, which are used to illustrate the technical solutions of the present invention, rather than to limit them. The protection scope of the present invention is not limited thereto. Although the present invention is described in detail with reference to the above-described embodiments, ordinary technicians in the field should understand that any technician familiar with the technical field can still modify the technical solutions recorded in the above-described embodiments within the technical scope disclosed by the present invention, or can easily think of changes, or make equivalent replacements for some of the technical features therein; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims

1. A method for querying enterprise information, characterized in that: The method is applied to a large search model, and the method comprises: Obtain enterprise query information from the user side; Using a deep learning analysis model and a preset attribute keyword table, data analysis and processing are performed on the enterprise query information to determine target query information, and an SQL statement is generated according to the target query information, wherein the target query information is information in the enterprise query information corresponding to the attribute keyword table; The SQL statement is matched with a preset database to determine target enterprise information, and the target enterprise information is sent to the user end.

2. The enterprise information query method according to claim 1, characterized in that: Before the step of obtaining the enterprise query information of the user terminal, the following steps are included: Obtaining user input information, and determining a query target of the user input information through the deep learning analysis model; The input information category is determined by presetting the screening conditions and based on the query target and the user identity information corresponding to the user input information.

3. The enterprise information query method according to claim 2, characterized in that: The step of determining the category of the input information by preset screening conditions based on the query target and the user address corresponding to the user input information includes: When the query target is enterprise screening, and the user identity information is a Chinese user, determining that the user input information is enterprise query information; When the query target is non-enterprise screening, or the user identity information is non-Chinese user, it is determined that the user input information is chat information, and the information query process is terminated.

4. The enterprise information query method according to claim 1, characterized in that: The step of using the deep learning analysis model and the preset attribute keyword table to perform data analysis and processing on the enterprise query information to determine the target query information includes: Extracting key attribute information from the enterprise query information according to the preset attribute keyword table; The key attribute information is subjected to data analysis and processing by the deep learning analysis model to determine the target query information.

5. The enterprise information query method according to claim 4, characterized in that: The step of extracting key attribute information from the enterprise query information according to the preset attribute keyword table includes: According to the priority of each attribute keyword in the preset attribute keyword table, keywords are extracted from the enterprise query information in descending order of priority to determine the key attribute information.

6. The enterprise information query method according to claim 4, characterized in that: The method comprises: When there is no content matching the preset attribute keyword table in the enterprise query information, a query failure notification is sent to the user terminal.

7. The enterprise information query method according to claim 4, characterized in that: After the step of performing data analysis and processing on the attribute keywords through the deep learning analysis model to determine the target query information, the method further includes: The target query information is filtered for invalid information, and the SQL statement is determined according to the filtered target query information, wherein the invalid information includes: information containing special fields.

8. An enterprise information query device, characterized in that: The device is applied to a large-scale search model, and the device comprises: Information acquisition module, which obtains enterprise query information from the user end; An information analysis module, using a deep learning analysis model and a preset attribute keyword table, performs data analysis and processing on the enterprise query information, determines target query information, and generates an SQL statement according to the target query information, wherein the target query information is information in the enterprise query information corresponding to the attribute keyword table; The information query module matches the SQL statement with a preset database, determines the target enterprise information, and sends the target enterprise information to the user end.

9. A server, characterized in that: The method comprises a processor and a memory, wherein the memory stores computer executable instructions that can be executed by the processor, and the processor executes the computer executable instructions to implement the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, and when the computer-executable instructions are called and executed by a processor, the computer-executable instructions prompt the processor to implement the method according to any one of claims 1 to 7.

Images