Agricultural information push processing method and system

Abstract

The invention discloses an agricultural information push processing method and system, and the method comprises the steps: selecting a first target agricultural information push queue from at least one first agricultural information push queue, determining a first target information matching degree between each piece of first target agricultural information in the first target agricultural information pushing queue and the first target request instruction; judging whether the first target information matching degree is greater than a preset matching degree threshold value or not; if the matching degree is greater than the matching degree threshold value, updating all the first agricultural information push queues according to an information crawling model to obtain an updated second agricultural information push queue; and pushing the second target agricultural information in the second target agricultural information pushing queue and the second agricultural information in other second agricultural information pushing queues to the corresponding at least one user. The problem of low pushing accuracy caused by high isomerism of agricultural information or fuzzy expression of user demands is solved.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of information pushing, and particularly relates to an agricultural information pushing processing method and system. BACKGROUND

[0002] With the development of agricultural informatization, agricultural data presents explosive growth, covering meteorological, soil, crop growth, market price and other multi-source heterogeneous information. Users (such as farmers, agricultural enterprises or researchers) usually obtain the required agricultural information through an information pushing system to assist production decision-making.

[0003] In the prior art, when agricultural information is highly heterogeneous (agricultural data sources are extensive, structures are various, including text, image, sensor data) or user demand is expressed ambiguously, although the information obtained by using an information crawling model based on the association expansion (such as semantic similarity) of keywords has a high coincidence degree with the keywords input by the user, the actual recommended agricultural information may only reflect surface correlation and ignore the difference of actual demand (such as region, crop variety, etc.), so that there is a large deviation between the actual recommended agricultural information and the actual demand of the user. SUMMARY

[0004] The present application provides an agricultural information pushing processing method and system to solve the technical problem of low pushing accuracy caused by strong heterogeneity of agricultural information or ambiguous expression of user demand.

[0005] In a first aspect, the present application provides an agricultural information pushing processing method, comprising: obtaining a request instruction of at least one user, and generating at least one agricultural information to-be-pushed queue according to the number of the request instructions; filling the at least one agricultural information to-be-pushed queue with agricultural information corresponding to the request instruction of the at least one user according to a preset information crawling model, to obtain at least one first agricultural information pushing queue after filling with agricultural information; comparing each first agricultural information pushing queue, selecting a first target agricultural information pushing queue from the at least one first agricultural information pushing queue according to a first comparison result, and determining a first target information matching degree between each first target agricultural information in the first target agricultural information pushing queue and a first target request instruction, wherein the target request instruction is a request instruction corresponding to the first target agricultural information pushing queue; judging whether the first target information matching degree is greater than a preset matching degree threshold; if greater than the matching degree threshold, updating all first agricultural information pushing queues according to the information crawling model to obtain updated second agricultural information pushing queues; compare each second agricultural information pushing queue, and select a second target agricultural information pushing queue from the each second agricultural information pushing queue according to a second comparison result until a second target information matching degree between the second target agricultural information pushing queue and a second target request instruction is greater than a preset matching degree threshold; push the second target agricultural information in the second target agricultural information pushing queue and second agricultural information in other second agricultural information pushing queues to the at least one user.

[0006] In a second aspect, the present application provides an agricultural information pushing processing system, comprising: a generating module configured to acquire request instructions of at least one user, and generate at least one agricultural information to-be-pushed queue according to a number of the request instructions; a crawling module configured to fill agricultural information corresponding to the request instructions of the at least one user in the at least one agricultural information to-be-pushed queue according to a preset information crawling model, and obtain at least one first agricultural information pushing queue after filling the agricultural information; a determining module configured to compare each first agricultural information pushing queue, select a first target agricultural information pushing queue from the at least one first agricultural information pushing queue according to a first comparison result, and determine a first target information matching degree between each first target agricultural information in the first target agricultural information pushing queue and a first target request instruction, wherein the target request instruction is a request instruction corresponding to the first target agricultural information pushing queue; a judging module configured to judge whether the first target information matching degree is greater than a preset matching degree threshold; an updating module configured to, if greater than the matching degree threshold, update all first agricultural information pushing queues according to the information crawling model, and obtain updated second agricultural information pushing queues; a selecting module configured to compare each second agricultural information pushing queue, and select a second target agricultural information pushing queue from the each second agricultural information pushing queue according to a second comparison result until a second target information matching degree between the second target agricultural information pushing queue and a second target request instruction is greater than a preset matching degree threshold; a pushing module configured to push the second target agricultural information in the second target agricultural information pushing queue and second agricultural information in other second agricultural information pushing queues to the at least one user.

[0007] In a third aspect, an electronic device is provided, comprising at least one processor, and a memory connected with the at least one processor in communication, wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the steps of the agricultural information pushing processing method of any of the embodiments of the present application.

[0008] In a fourth aspect, the present application further provides a computer readable storage medium, which stores a computer program, and the program instructions are executed by a processor to enable the processor to perform the steps of the agricultural information pushing processing method of any of the embodiments of the present application.

[0009] The agricultural information pushing processing method and system of the present application can select a first target agricultural information pushing queue from at least one first agricultural information pushing queue according to a first comparison result by comparing each first agricultural information pushing queue, and determine a first target information matching degree between each first target agricultural information in the first target agricultural information pushing queue and the first target request instruction, so as to compare the coincidence degree between the information obtained by analogy crawling according to the coincidence degree between the keywords input by the user. When the coincidence degree between the two is closer, the first target information matching degree is smaller. At this time, it is indicated that the information obtained by crawling is more consistent with the request instruction. Compared with the information crawling model which obtains agricultural information associated with the request instruction in a horizontal direction, the present application realizes updating in a vertical direction based on the comparison between the keywords to obtain agricultural information which is more matched with the request instruction of the user, and solves the problem of low pushing accuracy caused by strong heterogeneity of agricultural information or fuzzy expression of user demand. BRIEF DESCRIPTION OF DRAWINGS

[0010] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiment description. Obviously, the drawings in the following description are some embodiments of the present application, and other drawings can also be obtained by those skilled in the art without creative labor.

[0011] Figure 1 A flow chart of an agricultural information pushing processing method provided by an embodiment of the present application; Figure 2 A structural block diagram of an agricultural information pushing processing system provided by an embodiment of the present application; Figure 3 A structural schematic diagram of an electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0012] In order to make the purposes, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are some but not all of the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by a person of ordinary skill in the art without creative work fall within the protection scope of the present application.

[0013] Referring to Figure 1 , a flowchart of an agricultural information pushing processing method is shown.

[0014] As Figure 1 shown, the agricultural information pushing processing method specifically includes the following steps: Step S101, obtaining a request instruction of at least one user, and generating at least one agricultural information to-be-pushed queue according to the number of request instructions.

[0015] In this step, in an agricultural information service platform, a user can submit a request instruction for agricultural information acquisition through voice, text or selection of a label. The system needs to generate a corresponding agricultural information to-be-pushed queue according to the request instruction of the user, so as to match and push related agricultural information subsequently.

[0016] It should be noted that at least one request instruction of a user is obtained, and an initial agricultural information to-be-recommended queue same in number as the request instruction is generated; a keyword set corresponding to the request instruction of the user is obtained by extracting keywords from the request instruction of the user according to a preset semantic recognition model, wherein the keyword set contains at least one keyword; and a queue tag of each initial agricultural information to-be-recommended queue is determined according to the keyword set, so as to obtain at least one agricultural information to-be-pushed queue, wherein one queue tag corresponds to one keyword set.

[0017] For example, three users submit different agricultural information requests: User A (a grower) requests an instruction: "How to prevent and treat rice blast?". User B (a breeder) requests an instruction: "Common diseases and prevention methods of pig breeding"; User C (an agricultural machinery dealer) requests an instruction: "Price and performance comparison of the latest corn seeding machine in 2024"; Since there are three request instructions, the system first generates three initial agricultural information to-be-recommended queues, each corresponding to a user: queue Q1 (user A), queue Q2 (user B), and queue Q3 (user C).

[0018] The system uses a semantic recognition model to extract keywords from each request instruction and generate a queue label: ; At this time, the structures of the various initial agricultural information to-be-recommended queues are as follows: Queue Q1: to be filled with agricultural information related to “rice, rice blast, and prevention”; Queue Q2: to be filled with agricultural information related to “live pigs, breeding, diseases, and prevention”; Queue Q3: to be filled with agricultural information related to “corn planter, price, performance comparison, 2024”.

[0019] Specifically, the semantic recognition model can be obtained by training a neural network model. Therefore, no more details are provided here.

[0020] In step S102, according to a preset information crawling model, agricultural information corresponding to the request instruction of the at least one user is filled in the at least one agricultural information to-be-pushed queue, and at least one first agricultural information pushed queue after filling the agricultural information is obtained.

[0021] In this step, according to the information crawling model, agricultural information associated with each queue label is crawled; each agricultural information is filled into the agricultural information to-be-pushed queue corresponding to each queue label, and at least one first agricultural information pushed queue is obtained.

[0022] For example, the system uses an information crawling model to grab matching information from sources such as agricultural databases, news, papers, etc., and fills it into the initial agricultural information to-be-recommended queue. For example: Queue Q1 (rice blast prevention) may be filled with: “Identification and chemical control methods of rice blast”, “Application of biological pesticides in rice disease control”, and “Recommendation of rice blast-resistant varieties in 2024”; Queue Q2 (live pig breeding disease prevention) may be filled with: “Prevention and control measures for African swine fever”, “Common digestive diseases and treatment methods of live pigs”, and “Construction of biological safety system in modern pig farms”; Queue Q3 (comparison of corn planters) may be filled with: “Comparison of 2024 mainstream corn planters”, “Performance analysis of air suction vs. mechanical corn planters”, and “Application of intelligent seeders in corn planting”.

[0023] Step S103, comparing each first agricultural information push queue, selecting a first target agricultural information push queue from the at least one first agricultural information push queue according to a first comparison result, and determining a first target information matching degree between each first target agricultural information in the first target agricultural information push queue and a first target request instruction, wherein the target request instruction is a request instruction corresponding to the first target agricultural information push queue.

[0024] In this step, the queue tags of each first agricultural information push queue are obtained, and the number of queue sub-tags in each queue tag is determined; the queue tag with the largest number of tags is selected from each queue tag, defined as a first target queue tag, and a first target agricultural information push queue containing the first target queue tag is selected from the at least one first agricultural information push queue.

[0025] It should be noted that the more the number of tags, the richer the semantic dimension of user requests (such as "rice + rice blast + prevention + organic planting" contains more constraint conditions than single "rice"), and preferential processing of such queues can ensure the accuracy of information matching.

[0026] Further, the queue tag includes at least one queue sub-tag, wherein one queue sub-tag corresponds to one keyword. Determining the first target information matching degree between each first target agricultural information in the first target agricultural information push queue and the first target request instruction specifically includes: segmenting the first keyword and the second keyword in the first target request instruction to obtain at least one first vocabulary corresponding to the first keyword and at least one second vocabulary corresponding to the second keyword; calculating the word overlap degree between the first keyword and the second keyword according to the number of overlapping words between the at least one first vocabulary and the at least one second vocabulary and the total number of words, wherein when the number of words in the first vocabulary is greater than the number of words in the second vocabulary, the total number of words is the number of words in the first vocabulary, otherwise the total number of words is the number of words in the second vocabulary; determining a first queue sub-tag corresponding to the first keyword and a second queue sub-tag corresponding to the second keyword, and obtaining a first target agricultural information corresponding to the first queue sub-tag in the first target agricultural information push queue, defined as first information, and a first target agricultural information corresponding to the second queue sub-tag, defined as second information; determining the information overlap degree between the first information and the second information according to a preset information recognition model, and calculating the absolute value of the difference between the word overlap degree and the information overlap degree to obtain a target information sub-matching degree; calculating the absolute value of the difference between other word overlap degrees and other information overlap degrees to obtain other target information sub-matching degrees, and adding all target information sub-matching degrees to obtain the first target information matching degree.

[0027] In one specific application scenario, the user requests the instruction: "How to prevent and control rice blast and sheath blight?"; The extracted keyword set: ["rice", "blast", "sheath blight", "prevention and control"]; Generated queue sub-labels: Queue sub-label L1: rice; Queue sub-label L2: blast; Queue sub-label L3: sheath blight; Queue sub-label L4: prevention and control; The agricultural information already filled in the first target agricultural information push queue (Q1): Information A: "Chemical control methods for rice blast" (associated queue sub-labels: L2, L4); Information B: "Biological control techniques for sheath blight" (associated queue sub-labels: L3, L4); Information C: "Identification guide for common diseases of rice" (associated queue sub-labels: L1, L3); Step 1: Perform semantic segmentation on keywords based on domain knowledge graph or train models using annotated agricultural corpus, specifically: Select two keywords (e.g., "blast" and "sheath blight") from the user's request instruction for semantic segmentation: First keyword: "blast" → segmented into vocabulary set: ["blast", "fungus", "leaf disease"] Second keyword: "sheath blight" → segmented into vocabulary set: ["sheath blight", "fungus", "stem base disease"] Step 2: Calculate word overlap Number of overlapping words: There is one overlapping word "fungus"; Total number of words: The number of words in "blast" is 3, and the number of words in "sheath blight" is 3 → take the maximum value 3; Word overlap degree = number of overlapping words / total number of words = 1 / 3 ≈ 0.33; Step 3: Obtain information corresponding to queue sub-labels First queue sub-label (L2: blast) → associated information A; Second queue sub-label (L3: sheath blight) → associated information B; Select comparison information: Information (A): "Chemical control methods for rice blast"; Information (B): "Biological control techniques for sheath blight"; Step 4: Calculate information overlap Analyze the similarity of the two documents through an information recognition model (such as TF-IDF or BERT sentence vector): Both the title of information A and information B contain "disease" and "prevention", but the types of diseases and the methods of prevention are different.

[0028] Suppose the information overlap degree of the model output is 0.45 (range 0~1, the higher the value, the more similar).

[0029] Step 5: Calculate the target information sub-matching degree The absolute difference between the word overlap degree (0.33) and the information overlap degree (0.45) is |0.33-0.45|=0.12 The smaller this difference is, the more consistent the association between the keyword semantics and the information content is. In this example, the target information sub-matching degree is 0.12.

[0030] Step 6: Integrate all target information sub-matching degrees Repeat steps 1~5 to calculate the target information sub-matching degrees of other keyword combinations: For example, "rice" vs "prevention"→ target information sub-matching degree=0.08; "rice blast" vs "prevention"→ target information sub-matching degree=0.05; "rice blast" vs "prevention"→ target information sub-matching degree=0.10; The first target information matching degree is 0.12+0.08+0.05+0.10=0.35.

[0031] Step S104, determine whether the first target information matching degree is greater than a preset matching degree threshold.

[0032] In one specific embodiment, after determining whether the first target information matching degree is greater than the preset matching degree threshold, if it is not greater than the matching degree threshold, the first target agricultural information in the first target agricultural information push queue and the first agricultural information in other first agricultural information push queues are directly pushed to the corresponding at least one user.

[0033] Suppose the system's preset matching degree threshold is 0.30. The current first target information matching degree 0.35>0.30→determination is unqualified, then the first agricultural information push queue needs to be updated.

[0034] Step S105, if greater than the matching degree threshold, update all first agricultural information push queues according to the information crawling model to obtain an updated second agricultural information push queue.

[0035] In the embodiment, it is judged whether each target information sub-matching degree is greater than a preset threshold value; if a certain target information sub-matching degree is greater than the preset threshold value, a certain first information or a certain second information is removed from the first target agricultural information push queue, and the first target agricultural information corresponding to a certain first queue sub-label or a certain second queue sub-label is re-crawled according to the information crawling model; if all target information sub-matching degrees are not greater than the preset threshold value, other first information or other second information is removed from the first target agricultural information push queue from large to small based on the numerical size of the target information sub-matching degree, and the first target agricultural information corresponding to other first queue sub-label or other second queue sub-label is re-crawled according to the information crawling model until the first target information matching degree is not greater than the matching degree threshold value.

[0036] It should be noted that the definitions of "a certain", "first", "second", "other" and the like have no actual meaning and are only conventional definitions for referring to different objects. For example, a certain first information and a certain second information are the first target agricultural information corresponding to a certain first queue sub-label and the first target agricultural information corresponding to a certain second queue sub-label respectively; a certain target information sub-matching degree is the target information sub-matching degree between the first target agricultural information corresponding to a certain first queue sub-label and the first target agricultural information corresponding to a certain second queue sub-label.

[0037] In step S106, the second agricultural information push queues are compared, and a second target agricultural information push queue is selected from the second agricultural information push queues according to a second comparison result until a second target information matching degree between the second target agricultural information push queue and a second target request instruction is greater than a preset matching degree threshold value.

[0038] In step S107, the second target agricultural information in the second target agricultural information push queue and the second agricultural information in other second agricultural information push queues are pushed to the corresponding at least one user.

[0039] In this step, the other second agricultural information push queue is a queue obtained by removing the second target agricultural information push queue from all second agricultural information push queues.

[0040] To sum up, the method of the present application can compare each first agricultural information push queue, select a first target agricultural information push queue from at least one first agricultural information push queue according to a first comparison result, and determine a first target information matching degree between each first target agricultural information in the first target agricultural information push queue and the first target request instruction. The coincidence degree between the information obtained by analogy crawling and the keywords input by the user can be compared. When the coincidence degree between the two is closer, the first target information matching degree is smaller. At this time, it is indicated that the information obtained by crawling is more consistent with the request instruction. Compared with the information crawling model that obtains agricultural information associated with the request instruction horizontally, by setting an update rule based on the first target information matching degree, agricultural information that is more matched with the user request instruction is obtained by updating based on the comparison between the keywords vertically. The problem of low push accuracy caused by strong agricultural information heterogeneity or fuzzy user demand expression is solved.

[0041] Please refer to Figure 2 which shows a structural block diagram of an agricultural information push processing system of the present application.

[0042] As Figure 2 shown, the agricultural information push processing system 200 includes a generation module 210, a crawling module 220, a determination module 230, a judgment module 240, an update module 250, a selection module 260, and a push module 270.

[0043] The generation module 210 is configured to acquire a request instruction of at least one user, and generate at least one agricultural information to-be-pushed queue according to a quantity of the request instruction. The crawling module 220 is configured to fill, according to a preset information crawling model, the at least one agricultural information to-be-pushed queue with agricultural information corresponding to the request instruction of the at least one user, to obtain at least one first agricultural information pushed queue after filling with the agricultural information. The determination module 230 is configured to compare each first agricultural information pushed queue, select a first target agricultural information pushed queue from the at least one first agricultural information pushed queue according to a first comparison result, and determine a first target information matching degree between each first target agricultural information in the first target agricultural information pushed queue and a first target request instruction, wherein the target request instruction is a request instruction corresponding to the first target agricultural information pushed queue. The judgment module 240 is configured to judge whether the first target information matching degree is greater than a preset matching degree threshold value, and the matching degree threshold value is a matching degree threshold value dynamically set according to a quantity of the first target agricultural information in the first target agricultural information pushed queue. The update module 250 is configured to, if greater than the matching degree threshold value, update all the first agricultural information pushed queues according to the information crawling model, to obtain a second agricultural information pushed queue after updating. The selection module 260 is configured to compare each second agricultural information pushed queue, select a second target agricultural information pushed queue from the each second agricultural information pushed queue according to a second comparison result, until a second target information matching degree between the second target agricultural information pushed queue and a second target request instruction is greater than the preset matching degree threshold value. The pushing module 270 is configured to push second target agricultural information in the second target agricultural information pushed queue and second agricultural information in other second agricultural information pushed queues to corresponding at least one user.

[0044] It should be understood that Figure 2 The modules described above correspond to the respective steps in the method described above with reference to Figure 1 The operations and features described above with respect to the method, as well as the corresponding technical effects, are equally applicable to the modules, and thus will not be described again here. Figure 2 The operations and features described above with respect to the method, as well as the corresponding technical effects, are equally applicable to the modules, and thus will not be described again here.

[0045] In some embodiments, the present application also provides a computer readable storage medium having stored thereon a computer program, wherein the program instructions are executed by a processor to cause the processor to execute the agricultural information pushing method described above. As an implementation form, the computer readable storage medium of the present application stores computer executable instructions, and the computer executable instructions are configured to: Obtaining a request instruction of at least one user, and generating at least one agricultural information to-be-pushed queue according to the number of the request instruction; Filling agricultural information corresponding to the request instruction of the at least one user in the at least one agricultural information to-be-pushed queue according to a preset information crawling model, to obtain at least one first agricultural information pushed queue after filling agricultural information; Comparing each first agricultural information pushed queue, selecting a first target agricultural information pushed queue from the at least one first agricultural information pushed queue according to a first comparison result, and determining a first target information matching degree between each first target agricultural information in the first target agricultural information pushed queue and a first target request instruction, wherein the target request instruction is a request instruction corresponding to the first target agricultural information pushed queue; Determining whether the first target information matching degree is greater than a preset matching degree threshold; If greater than the matching degree threshold, updating all first agricultural information pushed queues according to the information crawling model, to obtain updated second agricultural information pushed queues; Comparing each second agricultural information pushed queue, selecting a second target agricultural information pushed queue from the each second agricultural information pushed queue according to a second comparison result, until a second target information matching degree between the second target agricultural information pushed queue and a second target request instruction is greater than a preset matching degree threshold; Pushing the second target agricultural information in the second target agricultural information pushed queue and the second agricultural information in other second agricultural information pushed queues to the corresponding at least one user.

[0046] The computer readable storage medium can include a program storage area and a data storage area, wherein the program storage area can store an operating system, at least one application required by a function; the data storage area can store data created according to the use of the agricultural information pushing processing system, etc. In addition, the computer readable storage medium can include a high-speed random access memory, and can also include a memory such as at least one magnetic disk storage device, a flash memory device, or other non-volatile solid-state memory device. In some embodiments, the computer readable storage medium can optionally include a memory remotely arranged relative to the processor, and these remote memories can be connected to the agricultural information pushing processing system through a network. Examples of the above network include but are not limited to the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof.

[0047] Figure 3 is a structural schematic diagram of an electronic device provided by an embodiment of the application, as Figure 3As shown, the device includes a processor 310 and a memory 320. The electronic device can also include an input device 330 and an output device 340. The processor 310, the memory 320, the input device 330 and the output device 340 can be connected by a bus or other means, Figure 3 The memory 320 is the computer readable storage medium described above. The processor 310 performs various functional applications and data processing of the server by running the non-volatile software programs, instructions and modules stored in the memory 320, that is, implements the agricultural information pushing processing method described above. The input device 330 can receive input digital or character information, and generate key signal input related to user settings and function control of the agricultural information pushing processing system. The output device 340 can include a display device such as a display screen.

[0048] The electronic device described above can perform the method provided by the embodiments of the present application, and has the corresponding function modules and beneficial effects of the method. Technical details not described in detail in the present embodiment can be referred to the method provided by the embodiments of the present application.

[0049] As an implementation, the electronic device described above is applied to an agricultural information pushing processing system, and is used for a client, including: at least one processor; and a memory in communication connection with the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to: obtain request instructions of at least one user, and generate at least one agricultural information to-be-pushed queue according to the number of the request instructions; fill agricultural information corresponding to the request instructions of the at least one user in the at least one agricultural information to-be-pushed queue according to a preset information crawling model, to obtain at least one first agricultural information pushing queue after filling agricultural information; compare each first agricultural information pushing queue, select a first target agricultural information pushing queue from the at least one first agricultural information pushing queue according to a first comparison result, and determine a first target information matching degree between each first target agricultural information in the first target agricultural information pushing queue and a first target request instruction, wherein the target request instruction is a request instruction corresponding to the first target agricultural information pushing queue; determine whether the first target information matching degree is greater than a preset matching degree threshold; if greater than the matching degree threshold, update all first agricultural information pushing queues according to the information crawling model, to obtain updated second agricultural information pushing queues; The second target agricultural information pushing queue is selected from the second agricultural information pushing queues according to a second comparison result until a second target information matching degree between the second target agricultural information pushing queue and the second target request instruction is greater than a preset matching degree threshold value; The second target agricultural information in the second target agricultural information pushing queue and the second agricultural information in the other second agricultural information pushing queues are pushed to the at least one user.

[0050] Through the above description of the embodiments, those skilled in the art can clearly understand that the embodiments can be realized by means of software and the necessary general hardware platform, and of course, can also be realized by hardware. Based on such understanding, the above technical solutions can be embodied in the form of a software product, which can be stored in a computer readable storage medium, such as a ROM / RAM, a magnetic disk, an optical disk, etc., and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods of the embodiments or some parts of the embodiments.

[0051] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, and not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: it can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement for some technical features; and these modifications 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 application.

Claims

1. A method for pushing agricultural information, characterized in that: include: Obtaining at least one user's request instruction, and generating at least one agricultural information to be pushed queue according to the number of the request instructions; Filling the at least one agricultural information to-be-pushed queue with agricultural information corresponding to the request instruction of the at least one user according to a preset information crawling model, thereby obtaining at least one first agricultural information push queue filled with agricultural information; Comparing each first agricultural information push queue, selecting a first target agricultural information push queue from the at least one first agricultural information push queue according to a first comparison result, and determining a first target information matching degree between each first target agricultural information in the first target agricultural information push queue and a first target request instruction, wherein the target request instruction is a request instruction corresponding to the first target agricultural information push queue; Determining whether the matching degree of the first target information is greater than a preset matching degree threshold; If the matching degree is greater than the threshold, all first agricultural information push queues are updated according to the information crawling model to obtain an updated second agricultural information push queue; Comparing each second agricultural information push queue, and selecting a second target agricultural information push queue from each second agricultural information push queue according to a second comparison result, until a second target information matching degree between the second target agricultural information push queue and the second target request instruction is greater than a preset matching degree threshold; The second target agricultural information in the second target agricultural information push queue and the second agricultural information in other second agricultural information push queues are pushed to the corresponding at least one user.

2. The agricultural information push processing method according to claim 1, characterized in that: Generating at least one agricultural information to be pushed queue according to the number of the request instructions includes: generating an initial agricultural information to-be-recommended queue having the same number as the request instructions; Performing keyword extraction on the request instruction of the at least one user according to a preset semantic recognition model to obtain a keyword set corresponding to the request instruction of the at least one user, wherein the keyword set includes at least one keyword; The queue labels of each initial agricultural information to be recommended queue are determined according to the keyword set to obtain at least one agricultural information to be pushed queue, wherein one queue label corresponds to one keyword set.

3. The agricultural information push processing method according to claim 2, characterized in that: The queue tag includes at least one queue subtag, wherein one queue subtag corresponds to one keyword; Determining the first target information matching degree between each first target agricultural information in the first target agricultural information push queue and the first target request instruction includes: Performing semantic segmentation on a first keyword and a second keyword in the first target request instruction to obtain at least one first word corresponding to the first keyword and at least one second word corresponding to the second keyword; Calculating a word overlap degree between the first keyword and the second keyword based on the word overlap number and the total word count between the at least one first word and the at least one second word, wherein when the word count of the first word is greater than the word count of the second word, the total word count is the word count of the first word, otherwise the total word count is the word count of the second word; Determine a first queue subtag corresponding to the first keyword and a second queue subtag corresponding to the second keyword, and obtain, in the first target agricultural information push queue, first target agricultural information corresponding to the first queue subtag, defined as first information, and first target agricultural information corresponding to the second queue subtag, defined as second information; Determining the information overlap between the first information and the second information according to a preset information recognition model, and calculating the absolute value of the difference between the word overlap and the information overlap to obtain a target information sub-matching degree; The absolute value of the difference between the overlap degree of other words and the overlap degree of other information is calculated to obtain the sub-matching degree of other target information, and all the sub-matching degrees of target information are added together to obtain the first target information matching degree.

4. The agricultural information push processing method according to claim 2, characterized in that: The step of filling the at least one agricultural information to-be-pushed queue with agricultural information corresponding to the request instruction of the at least one user according to a preset information crawling model, and obtaining at least one first agricultural information push queue filled with agricultural information, comprises: crawling agricultural information associated with each queue tag according to the information crawling model; Fill each agricultural information into the agricultural information to-be-pushed queue corresponding to each queue tag to obtain at least one first agricultural information push queue.

5. The agricultural information push processing method according to claim 3, characterized in that: The comparing the first agricultural information push queues and selecting a first target agricultural information push queue from the at least one first agricultural information push queue according to the first comparison result includes: Obtaining queue tags of each first agricultural information push queue, and determining the number of queue subtags in each queue tag; A queue tag with the largest number of tags is selected from the queue tags and defined as a first target queue tag, and a first target agricultural information push queue containing the first target queue tag is selected from the at least one first agricultural information push queue.

6. The agricultural information push processing method according to claim 1, characterized in that: After determining whether the matching degree of the first target information is greater than a preset matching degree threshold, the method further includes: If it is not greater than the matching degree threshold, the first target agricultural information in the first target agricultural information push queue and the first agricultural information in other first agricultural information push queues are directly pushed to the corresponding at least one user.

7. The agricultural information push processing method according to claim 3, characterized in that: The updating of all first agricultural information push queues according to the information crawling model to obtain the updated second agricultural information push queue includes: Determine whether the matching degree of each target information sub-item is greater than a preset threshold; If the sub-matching degree of a certain target information is greater than a preset threshold, the first information or the second information is removed from the first target agricultural information push queue, and the first target agricultural information corresponding to the first queue sub-tag or the second queue sub-tag is re-crawled according to the information crawling model; If the sub-matching degrees of all target information are not greater than the preset threshold, then based on the numerical value of the target information sub-matching degrees, other first information or other second information in the first target agricultural information push queue are removed from large to small, and the first target agricultural information corresponding to other first queue sub-tags or other second queue sub-tags are re-crawled according to the information crawling model until the matching degree of the first target information is no greater than the matching degree threshold.

8. An agricultural information push processing system, characterized in that: include: A generating module is configured to obtain a request instruction from at least one user and generate at least one agricultural information to be pushed queue according to the number of the request instructions; A crawling module is configured to fill the at least one agricultural information to-be-pushed queue with agricultural information corresponding to the request instruction of the at least one user according to a preset information crawling model, and obtain at least one first agricultural information push queue filled with agricultural information; a determination module configured to compare the first agricultural information push queues, select a first target agricultural information push queue from the at least one first agricultural information push queue according to a first comparison result, and determine a first target information matching degree between each first target agricultural information in the first target agricultural information push queue and a first target request instruction, wherein the target request instruction is a request instruction corresponding to the first target agricultural information push queue; a judgment module configured to judge whether the matching degree of the first target information is greater than a preset matching degree threshold; an updating module configured to update all first agricultural information push queues according to the information crawling model if the matching degree is greater than the matching degree threshold, to obtain an updated second agricultural information push queue; a selection module configured to compare the second agricultural information push queues and select a second target agricultural information push queue from the second agricultural information push queues according to a second comparison result, until a second target information matching degree between the second target agricultural information push queue and the second target request instruction is greater than a preset matching degree threshold; The push module is configured to push the second target agricultural information in the second target agricultural information push queue and the second agricultural information in other second agricultural information push queues to the corresponding at least one user.

9. An electronic device, characterized in that: include: At least one processor, and a memory communicatively connected to the at least one processor, wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images