An information collection method based on artificial intelligence

Abstract

The present invention discloses an information collection method based on artificial intelligence, and relates to the field of information retrieval technology. The method comprises: splitting a search formula used for information collection into multiple atomic search formulas; adding each atomic search formula in the multiple atomic search formulas to a built-in search queue and / or a general search queue based on the association relationship between the atomic search formulas; collecting information based on the latest built-in search queue and the latest general search queue to obtain multiple initial document information; dividing each initial document information in the multiple initial document information into multiple sentence sequences; calculating the correlation between all sentence sequences corresponding to each initial document information in the multiple initial document information and the multiple atomic search formulas, and filtering the multiple initial document information based on the correlation to obtain at least one target document information. The information collection method based on artificial intelligence disclosed by the present invention can improve the collection rate and accuracy of information.

Description

Technical Field

[0001] The present invention belongs to the technical field of information retrieval, and in particular relates to an information collection method based on artificial intelligence. Background Art

[0002] With the development of Internet technology, various search engines are widely used in information search and collection, such as Google, Baidu and other search engines.

[0003] At present, for information collection, most of the rule-based topic representation methods are used. The rule-based topic representation methods use several keywords and the "and" and "or" relationships between keywords to form a search formula for information collection. With the explosive growth of Internet information, the existing information collection methods have a low information collection rate due to the explosive growth of information, and it is increasingly difficult to meet the needs of practical applications. At the same time, the collected information also contains a large amount of content that is irrelevant to the information collected by the user, resulting in a poor user experience.

[0004] Therefore, how to provide an effective solution to improve the efficiency and accuracy of information collection has become a difficult problem to be solved in the prior art. Summary of the invention

[0005] The purpose of the present invention is to provide an information collection method based on artificial intelligence to solve the above-mentioned problems existing in the prior art.

[0006] In order to achieve the above object, the present invention adopts the following technical solutions:

[0007] In a first aspect, the present invention provides an information collection method based on artificial intelligence, comprising:

[0008] Splitting the search formula for information collection into multiple atomic search formulas, wherein the atomic search formula is a search formula that cannot be further split;

[0009] Based on the association relationship between each atomic search formula in the multiple atomic search formulas, each atomic search formula in the multiple atomic search formulas is added to the built-in search queue and / or the general search queue, wherein a plurality of first atomic search formulas having an interchange relationship are added to the general search queue, and one of the first atomic search formulas among the multiple first atomic search formulas is added to the built-in search queue, a plurality of second atomic search formulas having an inclusion relationship are added to the general search queue, and a second atomic search formula among the multiple second atomic search formulas containing other atomic search formulas is added to the built-in search queue, and one of the third atomic search formulas among the multiple third atomic search formulas having the same relationship is added to the built-in search queue and the general search queue;

[0010] Based on the latest built-in search queue and the latest general search queue, information is collected to obtain multiple initial document information;

[0011] Dividing each of the plurality of initial document information into a plurality of sentence sequences, wherein each sentence sequence includes a plurality of adjacent sentences;

[0012] Calculate the correlation between all sentence sequences corresponding to each of the multiple initial document information and the multiple atomic search formulas, and filter the multiple initial document information based on the correlation between all sentence sequences corresponding to each of the multiple initial document information and the multiple atomic search formulas to obtain at least one target document information.

[0013] Based on the above disclosed content, the present invention splits the search formula used for information collection into multiple atomic search formulas, where the atomic search formula is a search formula that cannot be further split; based on the association relationship between each atomic search formula in the multiple atomic search formulas, each atomic search formula in the multiple atomic search formulas is added to the built-in search queue and / or the general search queue, wherein multiple first atomic search formulas with an interchangeable relationship are added to the general search queue, and one of the multiple first atomic search formulas is added to the built-in search queue, multiple second atomic search formulas with an inclusion relationship are added to the general search queue, and the second atomic search formulas that contain other atomic search formulas in the multiple second atomic search formulas are added to the built-in Search queue, one of the third atomic search formulas with the same relationship is added to the built-in search queue and the general search queue; information is collected based on the latest built-in search queue and the latest general search queue to obtain multiple initial document information; each of the multiple initial document information is divided into multiple sentence sequences, wherein each sentence sequence includes multiple adjacent sentences; calculate the correlation between all sentence sequences corresponding to each of the multiple initial document information and the multiple atomic search formulas, and filter the multiple initial document information based on the correlation between all sentence sequences corresponding to each of the multiple initial document information and the multiple atomic search formulas to obtain at least one target document information. In this way, when collecting information, by adding each of the multiple atomic search formulas to the built-in search queue and / or the general search queue, repeated search of part of the information is avoided, thereby improving the information collection rate. At the same time, by calculating the correlation between all sentence sequences corresponding to the initial document information and the atomic search formula to filter the searched initial document information, some content that is irrelevant to the information collected by the user or has a low correlation can be filtered out, thereby improving the accuracy of information collection.

[0014] In a possible design, the relationship between the keywords in the search formula is an OR relationship or an AND relationship, and the search formula for information collection is split into multiple atomic search formulas, including:

[0015] From left to right, search whether there are multiple keywords in the search formula that are in an OR relationship;

[0016] When there are multiple keywords in an OR relationship in the search formula, the multiple keywords in an OR relationship are respectively combined with the remaining contents in the search formula in an AND relationship to obtain multiple atomic search formulas;

[0017] From left to right, searching whether there are multiple keywords in an OR relationship in the multiple atomic search expressions;

[0018] When there are multiple keywords in an OR relationship in any atomic search formula, the multiple keywords in any atomic search formula are combined with the remaining contents in any atomic search formula in an AND relationship until there are no multiple keywords in an OR relationship in all atomic search formulas.

[0019] In a possible design, adding each atomic search formula in the multiple atomic search formulas to a built-in search queue and / or a general search queue based on the association relationship between each atomic search formula in the multiple atomic search formulas includes:

[0020] When there are a plurality of first atomic search expressions in an interchangeable relationship among the plurality of atomic search expressions, the plurality of first atomic search expressions in an interchangeable relationship are added to the general search queue, and one of the plurality of first atomic search expressions is added to the built-in search queue;

[0021] When there are multiple second atomic search expressions in a containment relationship among the multiple atomic search expressions, the multiple second atomic search expressions in a containment relationship are added to the general search queue, and the second atomic search expressions that contain other atomic search expressions in the multiple second atomic search expressions are added to the built-in search queue;

[0022] When there are a plurality of third atomic search formulas with the same relationship among the plurality of atomic search formulas, any one of the plurality of third atomic search formulas with the same relationship is added to the built-in search queue and the general search queue.

[0023] In a possible design, dividing each of the plurality of initial document information into a plurality of sentence sequences includes:

[0024] Divide the i-th sentence to the i+j-th sentence in any initial document information into a sentence sequence, where the initial value of i is 1 and j is an integer greater than or equal to 2;

[0025] Let i be incremented by 1, and re-divide the i-th sentence to the i+j-th sentence in any initial document information into a sentence sequence until i+j=N, where N represents the total number of sentences corresponding to any initial document information.

[0026] In one possible design, the value of j is 2.

[0027] In a possible design, calculating the relevance between all sentence sequences corresponding to each of the plurality of initial document information and the plurality of atomic search formulas includes:

[0028] Based on keyword matching, the relevance between all sentence sequences corresponding to each of the plurality of initial document information and the plurality of atomic search expressions is calculated.

[0029] In a possible design, filtering the multiple initial document information based on the relevance between all sentence sequences corresponding to each of the multiple initial document information and the multiple atomic search formulas includes:

[0030] If all sentence sequences corresponding to any one of the multiple initial document information do not match any of the multiple atomic search formulas, then the any one of the initial document information is removed.

[0031] In a second aspect, the present invention provides an information collection device based on artificial intelligence, comprising:

[0032] A splitting unit, used to split the search formula for information collection into multiple atomic search formulas, wherein the atomic search formula is a search formula that cannot be further split;

[0033] An adding unit, used for adding each atomic search formula among the multiple atomic search formulas to a built-in search queue and / or a general search queue based on the association relationship between each atomic search formula among the multiple atomic search formulas, wherein a plurality of first atomic search formulas having an interchange relationship are added to the general search queue, and one of the first atomic search formulas among the multiple first atomic search formulas is added to the built-in search queue, a plurality of second atomic search formulas having an inclusion relationship are added to the general search queue, and a second atomic search formula among the multiple second atomic search formulas containing other atomic search formulas is added to the built-in search queue, and one of the third atomic search formulas among a plurality of third atomic search formulas having the same relationship is added to the built-in search queue and the general search queue;

[0034] An information collection unit, used for collecting information based on the latest built-in search queue and the latest general search queue to obtain multiple initial document information;

[0035] A division unit, configured to divide each of the plurality of initial document information into a plurality of sentence sequences, wherein each sentence sequence includes a plurality of adjacent sentences;

[0036] A filtering unit is used to calculate the correlation between all sentence sequences corresponding to each of the multiple initial document information and the multiple atomic search formulas, and filter the multiple initial document information based on the correlation between all sentence sequences corresponding to each of the multiple initial document information and the multiple atomic search formulas to obtain at least one target document information.

[0037] In a third aspect, the present invention provides an electronic device comprising a memory, a processor and a transceiver which are communicatively connected in sequence, wherein the memory is used to store a computer program, the transceiver is used to send and receive messages, and the processor is used to read the computer program to execute the artificial intelligence-based information collection method as described in the first aspect or any possible design of the first aspect.

[0038] In a fourth aspect, the present invention provides a computer-readable storage medium having instructions stored thereon, which, when executed on a computer, executes the artificial intelligence-based information collection method described in the first aspect or any possible design of the first aspect.

[0039] In a fifth aspect, the present invention provides a computer program product comprising instructions, which, when executed on a computer, causes the computer to execute the artificial intelligence-based information collection method as described in the first aspect or any possible design of the first aspect.

[0040] Beneficial effects:

[0041] When collecting information, the present invention avoids repeated searching of part of the information by adding each atomic search formula among multiple atomic search formulas to the built-in search queue and / or the general search queue, thereby improving the information collection rate. At the same time, by calculating the correlation between all sentence sequences corresponding to the initial document information and the atomic search formula, the searched initial document information is filtered, and some content that is irrelevant to or has a low correlation with the information collected by the user can be filtered out, thereby improving the accuracy of information collection, enhancing the user experience, and facilitating practical application and promotion. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 A flowchart of an information collection method based on artificial intelligence provided in an embodiment of the present application;

[0043] Figure 2 A schematic block diagram of an information collection device based on artificial intelligence provided in an embodiment of the present application;

[0044] Figure 3 A schematic block diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0045] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the present invention will be briefly introduced below in combination with the drawings and the description of the embodiments or the prior art. Obviously, the following description of the structure of the drawings is only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. It should be noted that the description of these embodiments is used to help understand the present invention, but does not constitute a limitation of the present invention.

[0046] It should be understood that although the terms first, second, etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are only used to distinguish one unit from another unit. For example, a first unit can be referred to as a second unit, and similarly, a second unit can be referred to as a first unit without departing from the scope of the exemplary embodiments of the present invention.

[0047] It should be understood that the term "and / or" that may appear in this article is merely a description of the association relationship between associated objects, indicating that three relationships may exist. For example, A and / or B can represent three situations: A exists alone, B exists alone, and A and B exist at the same time. The term " / and" that may appear in this article describes another type of association object relationship, indicating that two relationships may exist. For example, A / and B can represent two situations: A exists alone, and A and B exist alone. In addition, the character " / " that may appear in this article generally indicates that the previous and next associated objects are in an "or" relationship.

[0048] In order to facilitate the collection of information, an embodiment of the present application provides an information collection method based on artificial intelligence. The information collection method based on artificial intelligence can improve the efficiency and accuracy of information collection and enhance the user experience.

[0049] The information collection method based on artificial intelligence provided in the embodiment of the present application can be applied to the server of the search engine. It can be understood that the execution subject does not constitute a limitation on the embodiment of the present application.

[0050] The following is a detailed description of the information collection method based on artificial intelligence provided in the embodiments of the present application.

[0051] like Figure 1 As shown, it is a flowchart of the information collection method based on artificial intelligence provided in the first aspect of the embodiment of the present application. The information collection method based on artificial intelligence may include but is not limited to the following steps S101-S105.

[0052] Step S101: Split the search formula for information collection into multiple atomic search formulas.

[0053] Among them, the atomic search terms are search terms that cannot be further split.

[0054] In the embodiment of the present application, the search formula may be composed of keywords of the subject to be collected and the relationship between the keywords. The relationship between the keywords in the search formula may be divided into an or relationship or an and relationship. For example, "A*B(C+D)", where "*" represents an and relationship and "+" represents an or relationship.

[0055] When splitting the search formula used for information collection into multiple atomic search formulas, you can search from left to right to see whether there are multiple keywords in the search formula that are in an OR relationship. When there are no multiple keywords in the search formula that are in an OR relationship, the search is an atomic search formula and cannot be split any further.

[0056] When there are multiple keywords in the search formula that are in an OR relationship, the multiple keywords in the OR relationship can be combined with the rest of the search formula to obtain multiple atomic search formulas. Then continue to search from left to right whether there are multiple keywords in the OR relationship in the multiple atomic search formulas. If there are multiple keywords in the OR relationship in any atomic search formula, the multiple keywords in any atomic search formula are replaced with the rest of the content in any atomic search formula to combine with the relationship. Repeat the above steps until there are no multiple keywords in the OR relationship in all atomic search formulas.

[0057] For example, if the search formula is "A*B(C+D)", it can be split into the atomic search formula "A*B*C" and the atomic search formula "A*B*D".

[0058] Step S102: Based on the association relationship between the atomic search expressions in the multiple atomic search expressions, add the atomic search expressions in the multiple atomic search expressions to the built-in search queue and / or the general search queue.

[0059] Among them, multiple first atomic search formulas with interchangeable relationships are added to the general search queue, and one of the multiple first atomic search formulas is added to the built-in search queue, multiple second atomic search formulas with inclusion relationships are added to the general search queue, and the second atomic search formulas among the multiple second atomic search formulas that include other atomic search formulas are added to the built-in search queue, and one of the third atomic search formulas among multiple third atomic search formulas with the same relationship is added to the built-in search queue and the general search queue.

[0060] In an embodiment of the present application, in the process of adding each atomic search formula among multiple atomic search formulas to a built-in search queue and / or a general search queue, when there are multiple first atomic search formulas with an interchangeable relationship among the multiple atomic search formulas, the multiple first atomic search formulas with an interchangeable relationship are added to the general search queue, and one of the first atomic search formulas among the multiple first atomic search formulas is added to the built-in search queue.

[0061] When there are multiple second atomic search terms with an inclusion relationship among multiple atomic search terms, the multiple second atomic search terms with an inclusion relationship are added to the general search queue, and the second atomic search terms that contain other atomic search terms in the multiple second atomic search terms are added to the built-in search queue.

[0062] When there are a plurality of third atomic search formulas with the same relationship among the plurality of atomic search formulas, any one of the plurality of third atomic search formulas with the same relationship is added to the built-in search queue and the general search queue.

[0063] The multiple first atomic search formulas that are in an interchangeable relationship may refer to multiple first atomic search formulas that have the same keywords but in different orders. For example, the first atomic search formula A*B*C and the first atomic search formula A*C*B are first atomic search formulas that are in an interchangeable relationship.

[0064] Multiple second atomic search formulas that have an inclusion relationship may refer to multiple second atomic search formulas in which all keyword sets in a part of the second atomic search formulas are subsets of all keyword sets in another second atomic search formula. For example, multiple second atomic search formulas include a second search formula D*E and a second search formula D*E*F. Then, there is an inclusion relationship between the second search formula D*E*F and the second search formula D*E, and the second search formula D*E*F contains the second search formula D*E.

[0065] A plurality of third atomic search formulas having the same relationship may mean that the keywords of the plurality of third atomic search formulas are the same and the order of the keywords is also the same.

[0066] The built-in search queue mainly refers to the queue used by the search function integrated into a system, software or application. The advantages of the built-in search queue are high integration, fast response speed, and good adaptability to the needs of the system. However, since it is designed for a specific system, it may lack flexibility and be difficult to adapt to changes in the external environment. The general search queue refers to a more widely applicable queue mechanism that can be used in a variety of different search scenarios and applications. Compared with the built-in search queue, the general search queue has higher flexibility and scalability.

[0067] Since multiple first atomic search formulas with interchangeable relationships are added to the general search queue, and one of the multiple first atomic search formulas is added to the built-in search queue, multiple second atomic search formulas with inclusion relationships are added to the general search queue, and the second atomic search formulas containing other atomic search formulas in the multiple second atomic search formulas are added to the built-in search queue, and one of the multiple third atomic search formulas with the same relationship is added to the built-in search queue and the general search queue. Therefore, some atomic searches with interchangeable relationships, inclusion relationships, and the same relationship do not need to be repeatedly added to the search queue, thereby avoiding repeated searches, reducing the time consumption of information collection, and improving the efficiency of information collection.

[0068] Step S103: Collect information based on the latest built-in search queue and the latest general search queue to obtain multiple initial document information.

[0069] Among them, information collection through built-in search queues and general search queues is an existing technology and will not be explained here.

[0070] Step S104: Divide each of the multiple pieces of initial document information into multiple sentence sequences, wherein each sentence sequence includes multiple adjacent sentences.

[0071] Specifically, when each of the multiple initial document information is divided into multiple sentence sequences, the i-th sentence to the i+j-th sentence in any of the multiple initial document information can be divided into a sentence sequence, where the initial value of i is 1, and j is an integer greater than or equal to 2. Let i be incremented by 1, and the i-th sentence to the i+j-th sentence in any of the initial document information is re-divided into a sentence sequence until i+j=N, where N represents the total number of sentences corresponding to any of the initial document information. In the embodiment of the present application, the value of j is 2.

[0072] Step S105. Calculate the correlation between all sentence sequences corresponding to each of the multiple initial document information and the multiple atomic search formulas, and filter the multiple initial document information based on the correlation between all sentence sequences corresponding to each of the multiple initial document information and the multiple atomic search formulas to obtain at least one target document information.

[0073] In the embodiment of the present application, the correlation between all sentence sequences corresponding to each of the multiple initial document information and the multiple atomic search expressions may be calculated based on keyword matching.

[0074] Specifically, if all sentence sequences corresponding to any initial document information among the multiple initial document information do not match all atomic search formulas among the multiple atomic search formulas, then any initial document information is removed; otherwise, the initial document information is retained.

[0075] All sentence sequences corresponding to any initial document information do not match the atomic search formula, which may mean that all sentence sequences corresponding to any initial document information do not include all keywords in the atomic search formula.

[0076] By filtering multiple initial document information, some content that is irrelevant to or has a low correlation with the information collected by the user can be filtered out, thereby improving the accuracy of information collection.

[0077] In summary, the artificial intelligence-based information collection method provided by the present invention, when collecting information, avoids repeated searches of part of the information by adding each atomic search formula among multiple atomic search formulas to the built-in search queue and / or the general search queue, thereby improving the information collection rate. At the same time, by calculating the correlation between all sentence sequences corresponding to the initial document information and the atomic search formula, the searched initial document information is filtered, and some content that is irrelevant or has a low correlation with the information collected by the user can be filtered out, thereby improving the accuracy of information collection, enhancing the user experience, and facilitating practical application and promotion.

[0078] See also Figure 2 According to a second aspect of an embodiment of the present application, there is provided an information collection device based on artificial intelligence, the information collection device based on artificial intelligence comprising:

[0079] A splitting unit, used to split the search formula for information collection into multiple atomic search formulas, wherein the atomic search formula is a search formula that cannot be further split;

[0080] An adding unit, used for adding each atomic search formula among the multiple atomic search formulas to a built-in search queue and / or a general search queue based on the association relationship between each atomic search formula among the multiple atomic search formulas, wherein a plurality of first atomic search formulas having an interchange relationship are added to the general search queue, and one of the first atomic search formulas among the multiple first atomic search formulas is added to the built-in search queue, a plurality of second atomic search formulas having an inclusion relationship are added to the general search queue, and a second atomic search formula among the multiple second atomic search formulas containing other atomic search formulas is added to the built-in search queue, and one of the third atomic search formulas among a plurality of third atomic search formulas having the same relationship is added to the built-in search queue and the general search queue;

[0081] An information collection unit, used for collecting information based on the latest built-in search queue and the latest general search queue to obtain multiple initial document information;

[0082] A division unit, configured to divide each of the plurality of initial document information into a plurality of sentence sequences, wherein each sentence sequence includes a plurality of adjacent sentences;

[0083] A filtering unit is used to calculate the correlation between all sentence sequences corresponding to each of the multiple initial document information and the multiple atomic search formulas, and filter the multiple initial document information based on the correlation between all sentence sequences corresponding to each of the multiple initial document information and the multiple atomic search formulas to obtain at least one target document information.

[0084] The working process, working details and technical effects of the artificial intelligence-based information collection device provided in the second aspect of this embodiment can be found in the first aspect of the embodiment and will not be repeated here.

[0085] like Figure 3 As shown, the third aspect of an embodiment of the present application provides an electronic device, comprising a memory, a processor and a transceiver that are communicatively connected in sequence, wherein the memory is used to store computer programs, the transceiver is used to send and receive messages, and the processor is used to read the computer program to execute the artificial intelligence-based information collection method as described in the first aspect of the embodiment.

[0086] For specific examples, the memory may include but is not limited to random access memory (RAM), read-only memory (ROM), flash memory, first-in-first-out memory (FIFO) and / or first-in-last-out memory (FILO), etc.; the processor may be but is not limited to a microprocessor of the STM32F105 series, an ARM (Advanced RISC-Machines), an X86 or other architecture processor, or a processor with an integrated NPU (neural-network processing units); the transceiver may be but is not limited to a WiFi (Wireless Fidelity) wireless transceiver, a Bluetooth wireless transceiver, a General Packet Radio Service (GPRS) wireless transceiver, a ZigBee protocol (a low-power local area network protocol based on the IEEE802.15.4 standard, ZigBee) wireless transceiver, a 3G transceiver, a 4G transceiver and / or a 5G transceiver, etc.

[0087] The fourth aspect of this embodiment provides a computer-readable storage medium storing instructions including the information collection method based on artificial intelligence described in the first aspect of the embodiment, that is, the computer-readable storage medium stores instructions, and when the instructions are run on a computer, the information collection method based on artificial intelligence described in the first aspect is executed. The computer-readable storage medium refers to a carrier for storing data, which may include but is not limited to a floppy disk, an optical disk, a hard disk, a flash memory, a USB flash drive, and / or a memory stick, etc., and the computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices.

[0088] The fifth aspect of this embodiment provides a computer program product comprising instructions, which, when executed on a computer, enables the computer to execute the artificial intelligence-based information collection method as described in the first aspect of the embodiment, wherein the computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices.

[0089] It should be understood that certain details are provided in the following description to facilitate a complete understanding of the example embodiments. However, it should be understood by those of ordinary skill in the art that the example embodiments can be implemented without these certain details. For example, the system can be shown in a block diagram to avoid obscuring the example with unnecessary details. In other examples, well-known processes, structures, and techniques may not be shown in unnecessary detail to avoid obscuring the example embodiments.

[0090] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the protection scope of the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. An information collection method based on artificial intelligence, characterized in that: include: Splitting the search formula for information collection into multiple atomic search formulas, wherein the atomic search formula is a search formula that cannot be further split; Based on the association relationship between each atomic search formula in the multiple atomic search formulas, each atomic search formula in the multiple atomic search formulas is added to the built-in search queue and / or the general search queue, wherein a plurality of first atomic search formulas having an interchange relationship are added to the general search queue, and one of the first atomic search formulas among the multiple first atomic search formulas is added to the built-in search queue, a plurality of second atomic search formulas having an inclusion relationship are added to the general search queue, and a second atomic search formula among the multiple second atomic search formulas containing other atomic search formulas is added to the built-in search queue, and one of the third atomic search formulas among the multiple third atomic search formulas having the same relationship is added to the built-in search queue and the general search queue; Based on the latest built-in search queue and the latest general search queue, information is collected to obtain multiple initial document information; Dividing each of the plurality of initial document information into a plurality of sentence sequences, wherein each sentence sequence includes a plurality of adjacent sentences; Calculate the correlation between all sentence sequences corresponding to each of the multiple initial document information and the multiple atomic search formulas, and filter the multiple initial document information based on the correlation between all sentence sequences corresponding to each of the multiple initial document information and the multiple atomic search formulas to obtain at least one target document information.

2. The information collection method based on artificial intelligence according to claim 1, characterized in that: The relationship between the keywords in the search formula is an OR relationship or an AND relationship, and the search formula for information collection is split into multiple atomic search formulas, including: From left to right, search whether there are multiple keywords in the search formula that are in an OR relationship; When there are multiple keywords in an OR relationship in the search formula, the multiple keywords in an OR relationship are respectively combined with the remaining contents in the search formula in an AND relationship to obtain multiple atomic search formulas; From left to right, searching whether there are multiple keywords in an OR relationship in the multiple atomic search expressions; When there are multiple keywords in an OR relationship in any atomic search formula, the multiple keywords in any atomic search formula are combined with the remaining contents in any atomic search formula in an AND relationship until there are no multiple keywords in an OR relationship in all atomic search formulas.

3. The information collection method based on artificial intelligence according to claim 1 is characterized in that: The adding each of the multiple atomic search expressions to the built-in search queue and / or the general search queue based on the association relationship between each of the multiple atomic search expressions comprises: When there are a plurality of first atomic search expressions in an interchangeable relationship among the plurality of atomic search expressions, the plurality of first atomic search expressions in an interchangeable relationship are added to the general search queue, and one of the plurality of first atomic search expressions is added to the built-in search queue; When there are multiple second atomic search expressions in a containment relationship among the multiple atomic search expressions, the multiple second atomic search expressions in a containment relationship are added to the general search queue, and the second atomic search expressions that contain other atomic search expressions in the multiple second atomic search expressions are added to the built-in search queue; When there are a plurality of third atomic search formulas with the same relationship among the plurality of atomic search formulas, any one of the plurality of third atomic search formulas with the same relationship is added to the built-in search queue and the general search queue.

4. The information collection method based on artificial intelligence according to claim 1 is characterized in that: The step of dividing each of the plurality of initial document information into a plurality of sentence sequences includes: Divide the i-th sentence to the i+j-th sentence in any initial document information into a sentence sequence, where the initial value of i is 1 and j is an integer greater than or equal to 2; Let i be incremented by 1, and re-divide the i-th sentence to the i+j-th sentence in any initial document information into a sentence sequence until i+j=N, where N represents the total number of sentences corresponding to any initial document information.

5. The information collection method based on artificial intelligence according to claim 4 is characterized in that: The value of j is 2.

6. The information collection method based on artificial intelligence according to claim 1, characterized in that: The calculating the relevance between all sentence sequences corresponding to each of the plurality of initial document information and the plurality of atomic search formulas includes: Based on keyword matching, the relevance between all sentence sequences corresponding to each of the plurality of initial document information and the plurality of atomic search expressions is calculated.

7. The information collection method based on artificial intelligence according to claim 1 is characterized in that: The filtering of the plurality of initial document information based on the relevance between all sentence sequences corresponding to each of the plurality of initial document information and the plurality of atomic search formulas includes: If all sentence sequences corresponding to any one of the multiple initial document information do not match any of the multiple atomic search formulas, then the any one of the initial document information is removed.

8. An information collection device based on artificial intelligence, characterized in that: include: A splitting unit, used to split the search formula for information collection into multiple atomic search formulas, wherein the atomic search formula is a search formula that cannot be further split; An adding unit, used for adding each atomic search formula among the multiple atomic search formulas to a built-in search queue and / or a general search queue based on the association relationship between each atomic search formula among the multiple atomic search formulas, wherein a plurality of first atomic search formulas having an interchange relationship are added to the general search queue, and one of the first atomic search formulas among the multiple first atomic search formulas is added to the built-in search queue, a plurality of second atomic search formulas having an inclusion relationship are added to the general search queue, and a second atomic search formula among the multiple second atomic search formulas containing other atomic search formulas is added to the built-in search queue, and one of the third atomic search formulas among a plurality of third atomic search formulas having the same relationship is added to the built-in search queue and the general search queue; An information collection unit, used for collecting information based on the latest built-in search queue and the latest general search queue to obtain multiple initial document information; A division unit, configured to divide each of the plurality of initial document information into a plurality of sentence sequences, wherein each sentence sequence includes a plurality of adjacent sentences; A filtering unit is used to calculate the correlation between all sentence sequences corresponding to each of the multiple initial document information and the multiple atomic search formulas, and filter the multiple initial document information based on the correlation between all sentence sequences corresponding to each of the multiple initial document information and the multiple atomic search formulas to obtain at least one target document information.

9. An electronic device, characterized in that: It comprises a memory, a processor and a transceiver which are communicatively connected in sequence, wherein the memory is used to store a computer program, the transceiver is used to send and receive messages, and the processor is used to read the computer program to execute the artificial intelligence-based information collection method as described in any one of claims 1 to 7.

10. A computer program product comprising a computer program or instructions, characterized in that When the computer program or the instruction is executed by a computer, the information collection method based on artificial intelligence as described in any one of claims 1 to 7 is implemented.

Images