Generation method, device and equipment of intent enterprise electronic questionnaire, medium and product

Abstract

The invention discloses an intention enterprise electronic questionnaire generation method and device, equipment, a medium and a product. The method comprises the following steps: collecting large-scale enterprise related information of each enterprise, and mining the large-scale enterprise related information to obtain binary quantitative description values of each enterprise under a plurality of preset description dimensions; grouping the enterprises according to the binarized quantitative description values of the enterprises, and identifying a single measurement dimension pair and a contrast measurement dimension pair in the description dimensions according to a grouping result; constructing an editable intention enterprise questionnaire document according to the single measurement dimension and the contrast measurement dimension pair; in response to editing processing on at least one document of the editable intention enterprise questionnaire document, obtaining a target intention enterprise questionnaire document; and rendering the target intention enterprise questionnaire document to obtain an intention enterprise electronic questionnaire. According to the technical scheme provided by the embodiment of the invention, the labor cost of making the intentional enterprise electronic questionnaire is reduced, and the making efficiency of the intentional enterprise electronic questionnaire is improved.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, specifically to the field of AI (Artificial Intelligence) technology, and in particular to a method, device, equipment, medium and product for generating an electronic questionnaire for potential enterprises. Background Art

[0002] With the continuous development of mobile Internet technology and the emergence of various employment methods, job search applications that provide recruitment information for mobile Internet workers have appeared on the market. When workers register and become members of the job search application, the job search application can recommend various recruitment information customized to members to help members quickly join companies that meet their job search expectations.

[0003] In order to better recommend suitable recruitment information to users, after new members complete their registration, we can collect descriptive information about the companies they intend to work for through electronic questionnaires, and based on the collected information, quickly screen out target companies that meet the needs of new members.

[0004] Currently, the electronic questionnaires for potential companies used in job search applications often need to be manually constructed by experienced users based on the companies connected to the job search service platform, which is labor-intensive, time-consuming, and prone to errors. In addition, when new companies are connected to the job search service platform, or when the structure or benefits of the connected companies change, new electronic questionnaires for potential companies need to be rebuilt. In particular, when the above changes occur frequently, the labor costs and error rates will increase significantly. Summary of the invention

[0005] The embodiments of the present invention provide a method, device, equipment, medium and product for generating an electronic questionnaire of potential enterprises, so as to provide a new way to construct an electronic questionnaire of potential enterprises, reduce the manpower cost of producing the electronic questionnaire of potential enterprises, and improve the production efficiency of the electronic questionnaire of potential enterprises.

[0006] According to one aspect of an embodiment of the present invention, a method for generating an electronic questionnaire of potential enterprises is provided, comprising: Collect large-scale enterprise-related information of various enterprises on multiple platforms, and mine and process the information of various large-scale enterprises to obtain binary quantitative description values ​​of each enterprise under multiple preset description dimensions; The enterprises are grouped according to the binary quantitative description values ​​of each enterprise under each descriptive dimension, and based on the grouping results, a single measurement dimension and a comparison measurement dimension pair are identified in each descriptive dimension; Based on the identified single measurement dimensions and control measurement dimension pairs, a pre-trained AI model is used to build an editable prospective enterprise questionnaire document for each enterprise; In response to at least one document editing process on the editable potential enterprise questionnaire document, a target potential enterprise questionnaire document is obtained; The target intended enterprise questionnaire document is rendered to obtain an electronic questionnaire of the intended enterprise for providing to job seekers to fill in online.

[0007] According to another aspect of an embodiment of the present invention, there is also provided a device for generating an electronic questionnaire for potential enterprises, comprising: A quantitative description value acquisition module is used to collect large-scale enterprise-related information of various enterprises on multiple platforms, and mine and process the relevant information of each large-scale enterprise to obtain the binary quantitative description value of each enterprise under multiple preset description dimensions; A dimension identification module is used to group enterprises according to the binary quantitative description values ​​of each enterprise under each description dimension, and to identify a single measurement dimension and a comparison measurement dimension pair in each description dimension according to the grouping result; An editable questionnaire generation module is used to construct an editable prospective enterprise questionnaire document for each enterprise using a pre-trained artificial intelligence model based on the identified single measurement dimensions and control measurement dimension pairs; An editing response module, used for obtaining a target potential enterprise questionnaire document in response to at least one document editing process on the editable potential enterprise questionnaire document; The electronic questionnaire rendering module is used to render the target intended enterprise questionnaire document to obtain the intended enterprise electronic questionnaire for job seekers to fill out online.

[0008] According to another aspect of an embodiment of the present invention, an electronic device is provided, the electronic device comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the method for generating an electronic questionnaire for potential enterprises described in any embodiment of the present invention.

[0009] According to another aspect of an embodiment of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the method for generating an electronic questionnaire for potential enterprises described in any embodiment of the present invention when executed.

[0010] According to another aspect of an embodiment of the present invention, a computer program product is provided, including a computer program, which, when executed by a processor, implements the steps of the method for generating an electronic questionnaire for potential enterprises as described in any embodiment of the present invention.

[0011] The technical solution of the embodiment of the present invention collects large-scale enterprise-related information of each enterprise on multiple platforms, and mines and processes the large-scale enterprise-related information to obtain binary quantitative description values ​​of each enterprise under multiple preset description dimensions; groups the enterprises according to the binary quantitative description values ​​of each enterprise under each description dimension, and identifies a single measurement dimension and a comparison measurement dimension pair in each description dimension according to the grouping result; uses a pre-trained artificial intelligence model to construct an editable intended enterprise questionnaire document for each enterprise according to the identified single measurement dimension and the comparison measurement dimension pair; responds to at least one of the editable intended enterprise questionnaire documents The target enterprise questionnaire document is edited and processed to obtain the target enterprise questionnaire document; the target enterprise questionnaire document is rendered to obtain the implementation method of the electronic enterprise questionnaire for job seekers to fill out online. By using AI technology to deeply mine the key information of each enterprise, and constructing an editable enterprise questionnaire document based on the mining results, the labor cost of making the electronic questionnaire of the intended enterprise can be greatly reduced, and the production efficiency of the electronic questionnaire of the intended enterprise can be effectively improved. At the same time, users can perform manual fine-tuning of the intended enterprise questionnaire document on the editable enterprise questionnaire document conveniently, efficiently and without threshold, so as to further reduce labor costs.

[0012] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are 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.

[0014] Figure 1 is a flow chart of a method for generating an electronic questionnaire for potential enterprises according to an embodiment of the present invention; Figure 2 is a flow chart of another method for generating an electronic questionnaire for potential enterprises provided according to an embodiment of the present invention; Figure 3 is a flow chart of another method for generating an electronic questionnaire for potential enterprises provided according to an embodiment of the present invention; Figure 4 It is a schematic diagram showing a multi-dimensional scoring table and comprehensive description information applicable to the embodiment of the present invention; Figure 5It is a structural schematic diagram of a device for generating an electronic questionnaire for potential enterprises provided according to an embodiment of the present invention; Figure 6 It is a schematic diagram of the structure of an electronic device for implementing the method for generating an electronic questionnaire for potential enterprises according to an embodiment of the present invention. DETAILED DESCRIPTION

[0015] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0016] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0017] Figure 1 This is a flow chart of a method for generating an electronic questionnaire of intended enterprises provided in an embodiment of the present invention. This embodiment can be applied to the case where a job search service platform automatically constructs an electronic questionnaire of intended enterprises for accurately obtaining the job search intentions of registered members based on various information of the connected enterprises. This method can be executed by a device for generating an electronic questionnaire of intended enterprises, which can be implemented in the form of hardware and / or software, and can generally be configured in a job search service platform and used in conjunction with a job search client. Specifically, the job search service platform can be a single server or a server cluster composed of multiple servers, etc., and this embodiment does not limit this.

[0018] Correspondingly, such as Figure 1 As shown, the method may include: S110, collecting large-scale enterprise-related information of each enterprise on multiple platforms, and mining and processing each large-scale enterprise-related information to obtain a binary quantitative description value of each enterprise under multiple preset description dimensions.

[0019] As mentioned above, the method of this embodiment is mainly performed by a job search service platform, which is used in conjunction with a job search client. The job search service platform is pre-connected to multiple companies. When a job seeker installs the job search client and completes member registration in the job search client, the job search service platform can obtain companies suitable for the member from the connected companies through the job search client and recommend and match them to the member.

[0020] Accordingly, the above-mentioned enterprises can be understood as enterprises that are pre-connected to the job search service platform and are used to make job recommendations to members through the job search client.

[0021] In order to accurately recommend to members the companies they hope to join, it is necessary to first collect descriptive information about each company. Based on the above descriptive information, a quantitative description or portrait of each company can be made. Based on the quantitative description results, effective company recommendations can be made.

[0022] Among them, collecting large-scale enterprise-related information of various enterprises on multiple platforms can refer to obtaining various enterprise-related information maintained within the enterprise based on the open interface provided by the enterprise's local server, or querying and obtaining various enterprise-related information maintained by a third party from the enterprise information query interface provided by a third-party platform (for example, an industrial and commercial or tax platform, etc.); or, obtaining various enterprise-related information publicly released by the enterprise on an Internet platform (for example, various search engine platforms, social platforms or various types of information publishing platforms).

[0023] It is understandable that due to the variety of information collection methods, the data scale of the enterprise-related information collected in the end will also be very large. Therefore, the summary results of the above-mentioned enterprise-related information can be called large-scale enterprise-related information. Furthermore, considering that directly constructing the intended enterprise questionnaire based on the above-mentioned large-scale enterprise-related information is highly complex and will have greater noise interference, the inventors consider first using the powerful data mining and analysis capabilities of the AI ​​model to mine and process the large-scale enterprise-related information of each enterprise, and obtain information that is truly valuable for generating the intended enterprise questionnaire, that is: the binary quantitative description value of each enterprise under multiple preset description dimensions.

[0024] The above-mentioned description dimensions can be understood as a specific angle for describing the corporate image (portrait), for example, "corporate scale", "job content", "accommodation conditions", "work form" and "age requirements".

[0025] Correspondingly, the above-mentioned binary quantitative description value refers to an attribute value that quantitatively describes the description dimension through one of two preset specified values. For example, the binary quantitative description value corresponding to "enterprise scale" can be "less than 500 people" or "more than 500 people"; the binary quantitative description value corresponding to "work form" can be "standing work" or "sitting work".

[0026] In an optional implementation of this embodiment, mining and processing are performed on the relevant information of each large-scale enterprise to obtain a binary quantitative description value of each enterprise under multiple preset description dimensions, which may include: Obtain a pre-built dimension table, wherein the dimension table includes multiple description dimensions, and a first quantitative description value and a second quantitative description value corresponding to each description dimension; According to the dimension table and the preset prompt word template, a set of information mining prompt words corresponding to each enterprise is constructed; Each information mining prompt word in each information mining prompt word set is used to mine the binary quantitative description value of the set enterprise under the set description dimension to be the first quantitative description value or the second quantitative description value corresponding to the description dimension; The large-scale enterprise-related information and information mining prompt word set of each enterprise are respectively input into the pre-trained large language model to obtain the quantitative description value of each enterprise in each description dimension.

[0027] Specifically, a dimension table can be maintained in advance to store various description dimensions obtained through AI model mining or manually obtained through empirical summary, and two quantitative description values ​​corresponding to each description dimension can be determined, that is, the first quantitative description value and the second quantitative description value.

[0028] As mentioned above, the first quantitative description value corresponding to the description dimension of "enterprise scale" can be "less than 500 people", and the second quantitative description value can be "more than 500 people"; the first quantitative description value corresponding to "work form" can be "standing work", and the second quantitative description value can be "sitting work", etc.

[0029] It is understandable that the more quantitative description values ​​corresponding to a description dimension, the more accurate the characterization of the description dimension, but the higher the complexity of subsequent processing and analysis. In this embodiment, the quantitative description value of the description dimension is specifically concretized into two values ​​to effectively reduce the difficulty of subsequent data processing.

[0030] After obtaining the dimension table, a set of information mining prompt words corresponding to each enterprise can be constructed based on the preset prompt word template. Continuing with the previous example, a description word of the form "from the data of "XX enterprise", select a descriptive word from "standing work" and "sitting work" as the "work form" of "XX enterprise" can be constructed. In this example, the content in double quotes is the item to be filled in the prompt word template. By filling in the corresponding enterprise name, description dimension, and the first quantitative description value and the second quantitative description value corresponding to the description dimension in the matching item to be filled, a set of information mining prompt words corresponding to each enterprise can be constructed.

[0031] Based on the information mining prompt word set corresponding to each enterprise. By using various pre-built large language models, the quantitative description value of each enterprise under each description dimension can be effectively mined from the large-scale enterprise-related information corresponding to each enterprise. For example, the quantitative description value of enterprise A under the description dimension of "work form" is "standing work", while the quantitative description value of enterprise B under the description dimension of "work form" is "sitting work".

[0032] S120, grouping the enterprises according to the binary quantitative description values ​​of each enterprise under each description dimension, and identifying a single measurement dimension and a comparison measurement dimension pair in each description dimension according to the grouping result.

[0033] Among them, a single measurement dimension can be understood as one or more dimensions selected from each monomer tendency dimension included in each descriptive dimension. The monomer tendency dimension can be understood as a dimension that is strongly related to the user's personal enterprise intention tendency, and generally does not have a group tendency. For example, work form (standing work and sitting work), work environment (need to wear sterile clothing and no need to wear sterile clothing) and working hours description (long day shift and two shifts), etc. Each comparison measurement dimension pair contains two dimensions selected from each general tendency dimension in each descriptive dimension. The general tendency dimension can be understood as a dimension that is strongly related to the group enterprise intention tendency of most users. For example: accommodation conditions (4-person room or more than 4-person room), food situation (canteen provided or not provided) and comprehensive salary (less than AAAA yuan or more than AAAA yuan), etc.

[0034] In this embodiment, the enterprises can be grouped according to each binary quantitative description value under each description dimension. For example, the enterprises whose "working form" is "standing work" are grouped into {Enterprise 1, Enterprise 2, ..., and Enterprise n}, and the enterprises whose "working form" is "sitting work" are grouped into {Enterprise 11, Enterprise 22, ..., and Enterprise nn}, etc.

[0035] After completing the above enterprise grouping, single measurement dimensions and comparison measurement dimension pairs can be screened out based on all individual tendency dimensions and common tendency dimensions identified in each descriptive dimension.

[0036] In this embodiment, the purpose of screening single measurement dimensions and comparison measurement dimension pairs is to quickly screen out a few companies that meet the user's intentions from the limited user choices. For example, assuming that the grouping method of companies for "work form" is significantly different from the grouping method of companies for "work environment", by conducting questionnaire surveys using the above two dimensions as single measurement dimensions, a large number of companies that do not meet the user's intentions can be quickly screened out.

[0037] For another example, assuming that the grouping of companies with "food conditions" under "providing canteen" is obviously different from the grouping of companies with "comprehensive salary" under "less than AAAA yuan", therefore, the above two dimensions can be used to construct a comparison measurement dimension for questionnaire surveys, which can also quickly screen out a large number of companies that do not meet user expectations.

[0038] S130. Based on the identified single measurement dimension and the comparison measurement dimension pair, a pre-trained artificial intelligence model is used to construct an editable prospective enterprise questionnaire document for each enterprise.

[0039] In this embodiment, after effectively identifying a single measurement dimension and a comparison measurement dimension pair, an editable intended enterprise questionnaire document that can quickly determine the intended enterprises of recruiters can be efficiently constructed based on the above at least one single measurement dimension and at least one comparison measurement dimension pair.

[0040] In a specific example, if "working form" is identified as a single measurement dimension, an artificial intelligence model can be used to construct a questionnaire item in the form of "Are you willing to choose a standing working form?"; or, if "food conditions" and "comprehensive salary" are identified as a control measurement dimension pair, a questionnaire item in the form of "Are you willing to choose a job that provides a cafeteria but has an average comprehensive salary" can be constructed.

[0041] Of course, the above examples are only simple descriptions. In fact, any form of questionnaire items can be constructed, such as: picture selection or audio and video selection.

[0042] In this embodiment, training samples can be constructed for each standardized single measurement dimension and standardized control measurement dimension according to the actual questionnaire results, and the independently built artificial intelligence model or various open source large language models can be pre-trained to obtain an artificial intelligence model for generating a questionnaire for potential enterprises.

[0043] In this embodiment, the inventor further considers that it is often necessary to use manual verification to fine-tune the generated results of the artificial intelligence model. In order to improve the work efficiency of the questionnaire fine-tuning personnel, it is considered that the artificial intelligence model first generates an editable prospective enterprise questionnaire document, for example, a lightweight document in the form of .txt.

[0044] As shown above, the prospective enterprise questionnaire output by the artificial intelligence model may include pictures or videos, and then the storage address for storing the above pictures or videos may be added to the above-mentioned editable prospective enterprise questionnaire document, typically a URL (uniform resource locator) address. The questionnaire fine-tuning personnel may choose to click on the storage address to view the corresponding pictures or videos according to actual needs.

[0045] Through the above settings, questionnaire fine-tuning personnel do not need to have any page development experience. They can fine-tune the editable prospective enterprise questionnaire document by mastering certain document editing skills. For example, they can adjust the order of questions, add or delete specific questions, or fine-tune the question expressions, etc. This greatly reduces the technical threshold for questionnaire fine-tuning personnel. At the same time, this lightweight document editing method allows questionnaire fine-tuning personnel to fine-tune the editable prospective enterprise questionnaire document efficiently and conveniently on an ordinary terminal device (for example, a mobile phone).

[0046] S140. In response to at least one document editing process on the editable potential enterprise questionnaire document, a target potential enterprise questionnaire document is obtained.

[0047] After the questionnaire fine-tuning personnel complete one or more document editing tasks for the editable target enterprise questionnaire document, they can obtain the target enterprise questionnaire document that will be ultimately provided to job seekers.

[0048] S150: Rendering the target potential enterprise questionnaire document to obtain an electronic questionnaire of the target potential enterprise for providing to job seekers to fill out online.

[0049] In this embodiment, a document rendering component may be further developed to perform one-click rendering processing on the target intended enterprise questionnaire document to obtain the target intended enterprise questionnaire document that is ultimately provided to job seekers.

[0050] Furthermore, whenever a job seeker needs to obtain recommendation services for a potential enterprise, he or she may initiate a corresponding request to fill out a questionnaire, and the job search service platform may provide the target potential enterprise questionnaire document to the job seeker's job search client based on the request to fill out the questionnaire.

[0051] The technical solution of the embodiment of the present invention collects large-scale enterprise-related information of each enterprise on multiple platforms, and mines and processes the large-scale enterprise-related information to obtain binary quantitative description values ​​of each enterprise under multiple preset description dimensions; groups the enterprises according to the binary quantitative description values ​​of each enterprise under each description dimension, and identifies a single measurement dimension and a comparison measurement dimension pair in each description dimension according to the grouping result; uses a pre-trained artificial intelligence model to construct an editable intended enterprise questionnaire document for each enterprise according to the identified single measurement dimension and the comparison measurement dimension pair; responds to at least one document of the editable intended enterprise questionnaire document. The target enterprise questionnaire document is edited and processed to obtain the target intended enterprise questionnaire document; the target intended enterprise questionnaire document is rendered to obtain the implementation method of the intended enterprise electronic questionnaire for job seekers to fill out online. By using AI technology to deeply mine the key information of each enterprise, and constructing an editable intended enterprise questionnaire document based on the mining results, the labor cost of producing the intended enterprise electronic questionnaire can be greatly reduced, and the production efficiency of the intended enterprise electronic questionnaire can be effectively improved. At the same time, the questionnaire fine-tuning personnel can perform manual fine-tuning of the intended enterprise questionnaire document on the editable intended enterprise questionnaire document conveniently, efficiently and without threshold, so as to further reduce labor costs.

[0052] Based on the above embodiments, the job search service platform can regularly update and obtain large-scale enterprise-related information of each connected enterprise, and when the incremental data is larger than the preset data scale, it can choose to re-trigger the generation of a new electronic questionnaire of potential enterprises, so that job seekers can efficiently screen out potential enterprises that meet their actual needs from a large number of dynamically updated enterprises.

[0053] Figure 2 A flowchart of another method for generating an electronic questionnaire for potential enterprises provided in an embodiment of the present invention, this embodiment is optimized based on the above embodiments. In this embodiment, the operations of "grouping enterprises according to the binary quantitative description values ​​of each enterprise under each description dimension, and identifying a single measurement dimension and a comparison measurement dimension pair in each description dimension according to the grouping results" and "grouping enterprises according to the binary quantitative description values ​​under each general tendency dimension, and obtaining multiple comparison measurement dimension pairs with complementary enterprise relationships in each general tendency dimension according to the grouping results" are further refined.

[0054] Correspondingly, such as Figure 2 As shown, the method may include: S210, collecting large-scale enterprise-related information of each enterprise on multiple platforms, and mining and processing each large-scale enterprise-related information to obtain a binary quantitative description value of each enterprise under multiple preset description dimensions.

[0055] S220 , dividing the description dimension into a single tendency dimension and a general tendency dimension according to the binary quantitative description value under each description dimension.

[0056] In this embodiment, matching sentence pairs can be constructed based on the binary quantized description values ​​under each description dimension. By identifying the sentiment tendency of each sentence in the sentence pair, the description dimension can be divided into a single tendency dimension and a general tendency dimension.

[0057] In a specific example, "Sterile clothing is required in the working environment" and "Sterile clothing is not required in the working environment" can be used as a sentence pair, and the above sentence pair is input into a pre-trained sentiment tendency recognition model to determine the sentiment tendency ratio of the two sentences in the above sentence pair. Among them, the sentiment tendency can be understood as the proportion of the sentence with positive sentiment tendency, and the positive sentiment tendency can be understood as the emotion that positively motivates or stimulates ordinary users.

[0058] For example, the sentiment tendency of "need to wear sterile clothes in the work environment" accounts for 51%, while the sentiment tendency of "no need to wear sterile clothes in the work environment" accounts for 49%. Because the proportions of the two are very close, it can be considered that the descriptive dimension of "work environment" does not have a group-common sentiment tendency, which is basically a personal choice, and the descriptive dimension of "work environment" can be determined as a single tendency dimension. For another example, the sentiment tendency of "comprehensive salary is more than XXXX yuan" accounts for 92%, while the sentiment tendency of "comprehensive salary is less than XXXX yuan" accounts for 8%. Because the proportions of the two are very different, it can be considered that the descriptive dimension of "comprehensive salary" has a group-common sentiment tendency, and the descriptive dimension of "comprehensive salary" can be determined as a general tendency dimension.

[0059] Alternatively, multiple experienced experts may divide the preset multiple description dimensions into single tendency dimensions and general tendency dimensions through manual screening, and this embodiment does not limit this.

[0060] S230 , grouping enterprises according to the binary quantitative description values ​​under each monomer tendency dimension, and clustering each monomer tendency dimension according to the grouping result to obtain at least one monomer dimension cluster.

[0061] In this embodiment, for each identified monomer tendency dimension, each enterprise can be grouped according to two corresponding binary quantitative description values. For example, enterprise group 1 is obtained under one binary quantitative description value of monomer tendency dimension 1, enterprise group 2 is obtained under another binary quantitative description value of monomer tendency dimension 1, and enterprise group 3 is obtained under one binary quantitative description value of monomer tendency dimension 2, and enterprise group 4 is obtained under another binary quantitative description value of monomer tendency dimension 2.

[0062] As mentioned above, the purpose of constructing an electronic questionnaire of potential enterprises in various embodiments of the present invention is to quickly help job seekers screen out the potential enterprises they really need through the least number of questions. Therefore, when constructing questionnaire items through individual tendency dimensions, if the enterprise grouping methods of two different individual tendency dimensions are similar, then when constructing questionnaire items according to these two individual tendency dimensions separately, it is impossible to screen out enterprises that are not suitable for users through user selection. Therefore, each individual tendency dimension can first be clustered according to the grouping method of different individual tendency dimensions, that is, each individual tendency dimension with a similar grouping method is added to the same clustering cluster, that is, the individual dimension clustering cluster.

[0063] S240. Obtain at least one monomer tendency dimension in each monomer dimension cluster as a single measurement dimension.

[0064] Specifically, since the enterprise groupings of the monomer tendency dimensions in different monomer dimension clusters are quite different, one monomer tendency dimension can be selected from each monomer dimension cluster as a single measurement dimension.

[0065] Furthermore, in order to further limit the number of questionnaire items in the questionnaire survey, the number of individual dimension clustering clusters may be preset, and based on the preset number, each individual tendency dimension may be clustered.

[0066] S250, grouping enterprises according to the binary quantitative description values ​​under each general tendency dimension, and obtaining multiple comparison measurement dimension pairs having enterprise complementary relationships in each general tendency dimension according to the grouping result.

[0067] In an optional implementation of this embodiment, grouping enterprises according to the binary quantitative description values ​​under each general tendency dimension, and obtaining multiple comparison measurement dimension pairs having enterprise complementary relationships in each general tendency dimension according to the grouping result, may include: Identify the first quantitative description value and the second quantitative description value under each general tendency dimension as a positive quantitative description value and a negative quantitative description value; Obtain the positive enterprise groups under the positive quantitative description values ​​and the negative enterprise groups under the negative quantitative description values ​​for each general tendency dimension; If it is determined that the positive enterprise group of the first general tendency dimension and the negative enterprise group of the second general tendency dimension meet the preset difference condition, the first general tendency dimension and the second general tendency dimension are used as a comparison measurement dimension pair.

[0068] In this optional implementation, the first quantitative description value and the second quantitative description value under each general tendency dimension can be identified as positive quantitative description values ​​and negative quantitative description values ​​by manual determination or by identification by a sentiment tendency recognition model.

[0069] For example, if the sentiment tendency recognition model outputs a high proportion of sentiment tendency for a sentence, the binary quantitative description value contained in the sentence is identified as a positive quantitative description value, otherwise, it is identified as a negative quantitative description value.

[0070] Furthermore, by grouping enterprises according to the binary quantitative description values ​​under the universal tendency dimension, it is possible to obtain positive enterprise groups under positive quantitative description values ​​and negative enterprise groups under negative quantitative description values ​​for each universal tendency dimension. Furthermore, by comparing the difference between the positive enterprise groups and the negative enterprise groups under each universal tendency dimension, when the difference is greater than a preset threshold, the above two universal tendency dimensions can be selected to construct a comparison measurement dimension pair with a complementary relationship between enterprises.

[0071] For example, if there is a big difference between enterprise group A corresponding to the positive quantified description value of "food situation" "canteen provided" and enterprise group B corresponding to the negative quantified description value of "comprehensive salary" "less than AAAA yuan", then "food situation" and "comprehensive salary" can be used as a comparison measurement dimension.

[0072] It is understandable that by constructing a form such as "whether you tend to choose a job that provides a cafeteria but has a comprehensive salary below AAAA yuan" for this comparison measurement dimension, the intersection of two very different company groups can be calculated based on the job seekers' choices, to help job seekers quickly screen out the companies they need.

[0073] Of course, all feasible comparison measurement dimension pairs can be screened out through the above criteria, and then based on the model training results of the artificial intelligence model, the corresponding editable intended enterprise questionnaire documents can be efficiently and accurately constructed based on those typical comparison measurement dimension pairs.

[0074] Alternatively, all feasible comparison measurement dimension pairs may be provided to a pre-built expert model, and the expert model may first perform a round of screening of comparison measurement dimension pairs.

[0075] S260. Based on the identified single measurement dimensions and control measurement dimension pairs, a pre-trained artificial intelligence model is used to construct an editable prospective enterprise questionnaire document for each enterprise.

[0076] S270: In response to at least one document editing process on the editable potential enterprise questionnaire document, a target potential enterprise questionnaire document is obtained.

[0077] S280: Rendering the target potential enterprise questionnaire document to obtain an electronic questionnaire of the target potential enterprise for providing to job seekers to fill out online.

[0078] The technical solution of this embodiment divides the description dimension into a single tendency dimension and a general tendency dimension according to the binary quantitative description value under each description dimension; groups enterprises according to the binary quantitative description value under each single tendency dimension, and clusters each single tendency dimension according to the grouping result to obtain at least one single dimension clustering cluster; obtains at least one single tendency dimension in each single dimension clustering cluster as a single measurement dimension; groups enterprises according to the binary quantitative description value under each general tendency dimension, and obtains multiple control measurement dimension pairs with complementary enterprise relationships in each general tendency dimension according to the grouping result. This implementation method can efficiently obtain various general tendency dimensions and control measurement dimension pairs that can effectively screen the intended enterprises of job seekers from a large number of description dimensions used to characterize enterprises. Furthermore, the intended enterprises can be accurately screened through less questionnaire content, which greatly improves the efficiency of determining the intended enterprises and also improves the job seekers' satisfaction with the job search application to a certain extent.

[0079] Figure 3 This is a flow chart of another method for generating an electronic questionnaire of intended enterprises provided in an embodiment of the present invention. This embodiment is optimized based on the above embodiments. In this embodiment, after constructing the electronic questionnaire of intended enterprises, the specific implementation method of recommending enterprises to job seekers is further limited based on the results of job seekers filling out the electronic questionnaire of intended enterprises.

[0080] Correspondingly, such as Figure 3 As shown, the method may include: S310, collecting large-scale enterprise-related information of each enterprise on multiple platforms, and mining and processing the large-scale enterprise-related information to obtain binary quantitative description values, detailed description information and scoring values ​​of each enterprise under multiple preset description dimensions.

[0081] In this embodiment, it is considered that after providing the intended enterprise to the job seeker, the job seeker often needs to have a more detailed understanding of the intended enterprise. At this time, only based on the binary quantitative description value of the intended enterprise under multiple preset description dimensions, it is impossible to meet the job seeker's need for in-depth understanding of the enterprise. Based on this, while obtaining the binary quantitative description value of each enterprise under multiple preset description dimensions, further mining and processing the relevant information of each large-scale enterprise can be used to obtain detailed description information and scoring values ​​of each enterprise under multiple preset description dimensions.

[0082] For example, a large language model and pre-built prompt word templates can also be used to effectively mine detailed description information and scoring values ​​of each enterprise under multiple preset description dimensions.

[0083] For example, for the description dimension of "food conditions", you can construct forms such as: "Please use natural language to describe the "food conditions" of "XX Company" in detail", and "If the score range is 1-5 points, please score the "food conditions" of "XX Company"".

[0084] S320, grouping the enterprises according to the binary quantitative description values ​​of each enterprise under each description dimension, and identifying a single measurement dimension and a comparison measurement dimension pair in each description dimension according to the grouping result.

[0085] S330. Based on the identified single measurement dimension and the comparison measurement dimension pair, a pre-trained artificial intelligence model is used to construct an editable prospective enterprise questionnaire document for each enterprise.

[0086] S340: In response to at least one document editing process on the editable potential enterprise questionnaire document, a target potential enterprise questionnaire document is obtained.

[0087] S350: Rendering the target potential enterprise questionnaire document to obtain an electronic questionnaire of the target potential enterprise for providing to job seekers to fill out online.

[0088] S360: In response to the questionnaire filling request sent by the job-seeking client, an electronic questionnaire of the intended enterprise is provided to the job-seeking client for display so that the job-seeker can fill in the questionnaire online.

[0089] S370. Screen out a first number of predicted potential enterprises from among the enterprises according to the online questionnaire filling results of the job-seeking client in response to the electronic questionnaire of the potential enterprises.

[0090] The first quantity may be preset according to actual conditions, for example, 3, 4 or 5.

[0091] It is understandable that after obtaining the online questionnaire filling results of job seekers based on the feedback of the job search client, a certain number of intended enterprises that meet the user's questionnaire filling content can be screened out. If the number of intended enterprises screened out is more than the first number, the intended enterprises can be screened according to a certain screening strategy (for example, a random screening strategy, or a balanced exposure strategy, etc.) to obtain the first number of predicted intended enterprises; and if the number of intended enterprises screened out is less than the first number, one or more other enterprises can be selected according to a certain adding strategy (for example, a new access enterprise priority exposure strategy) to form the first number of predicted intended enterprises together with the intended enterprises.

[0092] Furthermore, considering that the results of the electronic questionnaire filled out by job seekers for the intended companies often involve user privacy, it is often necessary to encrypt the data of the online questionnaire filling results and store the data in encrypted form to prevent the job seekers' private data from being leaked.

[0093] S380. Under each description dimension, select a second number of target description dimensions, and generate a multi-dimensional scoring chart for each predicted potential enterprise under each target description dimension.

[0094] In this embodiment, the second number can be preset according to actual conditions, for example, it can be 5, 6 or 8. The above target description dimensions can be preset according to actual conditions, for example, through actual experience or model reasoning, a description dimension can be selected from multiple description dimensions, or a description dimension that best represents a corporate image or recruitment competitiveness can be obtained by integrating and summarizing multiple description dimensions as the target description dimension.

[0095] In a specific example, the target description dimensions may include: salary and benefits, accommodation conditions, recruitment requirements, and resignation policies, etc.

[0096] S390. Input the detailed description information of each predicted potential enterprise under each description dimension into the pre-trained large language model to obtain comprehensive description information that matches each predicted potential enterprise.

[0097] S3100, providing the multi-dimensional scoring chart and comprehensive description information corresponding to each predicted intended enterprise to the job search client for display in separate items.

[0098] Among them, Figure 4 FIG. 2 shows a schematic diagram of a multi-dimensional scoring table and comprehensive description information applicable to an embodiment of the present invention. Figure 4As shown in the figure, after the job seeker completes the electronic questionnaire of the intended enterprise, the job search service platform can automatically select 5 enterprises suitable for the job seeker and provide them to the job seeker in separate items. In the display sub-interface corresponding to each enterprise, a five-dimensional scoring chart and comprehensive description information for the enterprise are also included ( Figure 4 description of the reasons for the recommendation).

[0099] S3110. In response to the enterprise comparison request sent by the job-seeking client, a list of enterprises consisting of predicted potential enterprises is provided to the job-seeking client for display.

[0100] In this embodiment, when a job seeker views the display sub-interface of each predicted intended enterprise, a comparison control (for example, Figure 4 When the job seeker triggers and selects the comparison control, the enterprise comparison request can be triggered accordingly. When the job search service platform receives the enterprise comparison request, it can provide the enterprise list consisting of the predicted intended enterprises to the job search client, so that the job seeker can select multiple target predicted intended enterprises for comparison based on the job search client in the enterprise list.

[0101] S3120, in response to the job-seeking client selecting multiple target predicted potential enterprises for comparison in the enterprise list.

[0102] S3130. Construct a multi-dimensional enterprise comparison table based on the detailed description information of each target predicted intended enterprise under each description dimension, and provide the multi-dimensional enterprise comparison table to the job search client for display.

[0103] Specifically, a multi-dimensional enterprise comparison table such as Table 1 can be constructed to allow job seekers to quickly determine the enterprise they expect to join by comparing multiple enterprises horizontally. The last item in Table 1 can be automatically generated by a preset large language model based on detailed description information of different enterprises under the same description dimension, so as to provide job seekers with a more intuitive comparison result.

[0104] Table 1 Comparison Dimensions Company A Company B Comparative evaluation and recommendation Enterprise scale 200 people 2000 people Company B is larger and more stable Accommodation Free, 4-person room Free, 8-person room The accommodation conditions of enterprise A are significantly better than those of enterprise B.

[0105] The technical solution of the embodiment of the present invention is to respond to the intention questionnaire filling request sent by the job-seeking client, provide the electronic questionnaire of the intended enterprise to the job-seeking client for display, so that the job seeker can fill in the questionnaire online; according to the online questionnaire filling results fed back by the job-seeking client for the electronic questionnaire of the intended enterprise, screen out a first number of predicted intended enterprises from each of the enterprises; under each description dimension, select a second number of target description dimensions, and generate a multi-dimensional scoring chart of each predicted intended enterprise under each target description dimension; respectively input the detailed description information of each predicted intended enterprise under each description dimension into a pre-trained large language model; In the model, comprehensive descriptive information that matches each predicted intention enterprise is obtained; the multi-dimensional scoring chart and comprehensive descriptive information corresponding to each predicted intention enterprise are provided to the job search client for display in separate items. The enterprises that meet the actual intentions of job seekers can be provided to job seekers in a clear, intuitive, quantifiable and comparable manner. The enterprise that job seekers ultimately choose to join can meet the actual needs of job seekers to the greatest extent, minimize the frequent change of joining enterprises due to enterprise mismatch, and maximize the user satisfaction of job seekers with the job search application.

[0106] Figure 5 The structure diagram of a device for generating an electronic questionnaire for potential enterprises provided by an embodiment of the present invention is shown in FIG. Figure 5 As shown, the device includes: a quantitative description value acquisition module 510, a dimension identification module 520, an editable questionnaire generation module 530, an editing response module 540, and an electronic questionnaire rendering module 550.

[0107] The quantitative description value acquisition module 510 is used to collect large-scale enterprise-related information of each enterprise on multiple platforms, and mine and process the large-scale enterprise-related information to obtain binary quantitative description values ​​of each enterprise under multiple preset description dimensions; A dimension identification module 520 is used to group enterprises according to the binary quantitative description values ​​of each enterprise under each description dimension, and identify a single measurement dimension and a comparison measurement dimension pair in each description dimension according to the grouping result; An editable questionnaire generation module 530 is used to construct an editable prospective enterprise questionnaire document for each enterprise using a pre-trained artificial intelligence model based on the identified single measurement dimension and the comparison measurement dimension pair; An editing response module 540 is used to obtain a target potential enterprise questionnaire document in response to at least one document editing process on the editable potential enterprise questionnaire document; The electronic questionnaire rendering module 550 is used to render the target intended enterprise questionnaire document to obtain an electronic questionnaire of the intended enterprise for providing to job seekers to fill in online.

[0108] The technical solution of the embodiment of the present invention collects large-scale enterprise-related information of each enterprise on multiple platforms, and mines and processes the large-scale enterprise-related information to obtain binary quantitative description values ​​of each enterprise under multiple preset description dimensions; groups the enterprises according to the binary quantitative description values ​​of each enterprise under each description dimension, and identifies a single measurement dimension and a comparison measurement dimension pair in each description dimension according to the grouping result; uses a pre-trained artificial intelligence model to construct an editable intended enterprise questionnaire document for each enterprise according to the identified single measurement dimension and the comparison measurement dimension pair; responds to at least one of the editable intended enterprise questionnaire documents The target enterprise questionnaire document is edited and processed to obtain the target enterprise questionnaire document; the target enterprise questionnaire document is rendered to obtain the implementation method of the electronic enterprise questionnaire for job seekers to fill out online. By using AI technology to deeply mine the key information of each enterprise, and constructing an editable enterprise questionnaire document based on the mining results, the labor cost of making the electronic questionnaire of the intended enterprise can be greatly reduced, and the production efficiency of the electronic questionnaire of the intended enterprise can be effectively improved. At the same time, users can perform manual fine-tuning of the intended enterprise questionnaire document on the editable enterprise questionnaire document conveniently, efficiently and without threshold, so as to further reduce labor costs.

[0109] Based on the above embodiments, the quantitative description value acquisition module 510 can be specifically used for: Obtain a pre-built dimension table, wherein the dimension table includes multiple description dimensions, and a first quantitative description value and a second quantitative description value corresponding to each description dimension; According to the dimension table and the preset prompt word template, a set of information mining prompt words corresponding to each enterprise is constructed; Each information mining prompt word in each information mining prompt word set is used to mine the binary quantitative description value of the set enterprise under the set description dimension to be the first quantitative description value or the second quantitative description value corresponding to the description dimension; The large-scale enterprise-related information and information mining prompt word set of each enterprise are respectively input into the pre-trained large language model to obtain the quantitative description value of each enterprise in each description dimension.

[0110] Based on the above embodiments, the dimension identification module 520 may include: A dimension division unit, used for dividing the description dimension into a single tendency dimension and a general tendency dimension according to the binary quantitative description value under each description dimension; A cluster acquisition unit is used to group enterprises according to the binary quantitative description value under each monomer tendency dimension, and cluster each monomer tendency dimension according to the grouping result to obtain at least one monomer dimension cluster; A single measurement dimension acquisition unit, used for acquiring at least one single tendency dimension in each single dimension cluster as a single measurement dimension; The comparison measurement dimension pair acquisition unit is used to group enterprises according to the binary quantitative description values ​​under each general tendency dimension, and obtain multiple comparison measurement dimension pairs with enterprise complementary relationships in each general tendency dimension according to the grouping results.

[0111] Based on the above embodiments, the acquisition unit can be specifically used to: Identify the first quantitative description value and the second quantitative description value under each general tendency dimension as a positive quantitative description value and a negative quantitative description value; Obtain the positive enterprise groups under the positive quantitative description values ​​and the negative enterprise groups under the negative quantitative description values ​​for each general tendency dimension; If it is determined that the positive enterprise group of the first general tendency dimension and the negative enterprise group of the second general tendency dimension meet the preset difference condition, the first general tendency dimension and the second general tendency dimension are used as a comparison measurement dimension pair.

[0112] On the basis of the above embodiments, the present invention may further include: a detailed information acquisition module, which is used to mine the relevant information of each large-scale enterprise to obtain the binary quantitative description value of each enterprise under multiple preset description dimensions, and then mine the relevant information of each large-scale enterprise to obtain the detailed description information and score value of each enterprise under multiple preset description dimensions; Accordingly, the first type of information display module may also be included, which is used to: After obtaining the electronic questionnaire of the intended enterprise for providing to the job seeker for online filling, in response to the request for filling in the intended questionnaire sent by the job seeker client, the electronic questionnaire of the intended enterprise is provided to the job seeker client for display so that the job seeker can fill in the questionnaire online; Screening out a first number of predicted intended enterprises from each of the enterprises according to the online questionnaire filling results of the job-seeking client in response to the electronic questionnaire of the intended enterprises; Under each description dimension, a second number of target description dimensions are selected, and a multi-dimensional scoring chart of each forecast intention enterprise under each target description dimension is generated; Input the detailed description information of each predicted potential enterprise under each description dimension into the pre-trained large language model to obtain the comprehensive description information matching each predicted potential enterprise; The multi-dimensional scoring chart and comprehensive descriptive information corresponding to each predicted potential enterprise will be provided to the job-seeking client for display in separate items.

[0113] On the basis of the above embodiments, the second information display module may also be included, which is used to: After providing the multi-dimensional scoring graphs and comprehensive description information corresponding to each predicted intended enterprise to the job-seeking client for display, in response to an enterprise comparison request sent by the job-seeking client, providing the enterprise list consisting of each predicted intended enterprise to the job-seeking client for display; In response to the job-seeking client selecting multiple target predicted intended enterprises for comparison in the enterprise list; Based on the detailed description information of each target predicted intention enterprise under each description dimension, a multi-dimensional enterprise comparison table is constructed, and the multi-dimensional enterprise comparison table is provided to the job search client for display.

[0114] The device for generating an electronic questionnaire for potential enterprises provided in an embodiment of the present invention can execute the method for generating an electronic questionnaire for potential enterprises provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0115] In the technical solution of the present disclosure, the collection, storage, use, processing, transmission, provision and disclosure of user personal information involved are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0116] Figure 6 A schematic diagram of the structure of an electronic device 10 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0117] like Figure 6As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. The input / output (I / O) interface 15 is also connected to the bus 14.

[0118] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0119] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as executing the method for generating an electronic questionnaire for prospective enterprises as described in any one of the embodiments of the present invention.

[0120] That is: collect large-scale enterprise-related information of each enterprise on multiple platforms, and mine and process the information of each large-scale enterprise to obtain binary quantitative description values ​​of each enterprise under multiple preset description dimensions; The enterprises are grouped according to the binary quantitative description values ​​of each enterprise under each descriptive dimension, and based on the grouping results, a single measurement dimension and a comparison measurement dimension pair are identified in each descriptive dimension; Based on the identified single measurement dimensions and control measurement dimension pairs, a pre-trained AI model is used to build an editable prospective enterprise questionnaire document for each enterprise; In response to at least one document editing process on the editable potential enterprise questionnaire document, a target potential enterprise questionnaire document is obtained; The target intended enterprise questionnaire document is rendered to obtain an electronic questionnaire of the intended enterprise for providing to job seekers to fill in online.

[0121] In some embodiments, the method for generating an electronic questionnaire for potential enterprises as described in any one of the embodiments of the present invention may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the method for generating an electronic questionnaire for potential enterprises as described in any one of the embodiments of the present invention described above may be executed. Alternatively, in other embodiments, the processor 11 may be configured to execute the method for generating an electronic questionnaire for potential enterprises as described in any one of the embodiments of the present invention by any other appropriate means (for example, by means of firmware).

[0122] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0123] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0124] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, device, or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0125] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0126] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0127] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0128] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0129] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for generating an electronic questionnaire for potential enterprises, characterized in that: include: Collect large-scale enterprise-related information of various enterprises on multiple platforms, and mine and process the information of various large-scale enterprises to obtain binary quantitative description values ​​of each enterprise under multiple preset description dimensions; The enterprises are grouped according to the binary quantitative description values ​​of each enterprise under each descriptive dimension, and based on the grouping results, a single measurement dimension and a comparison measurement dimension pair are identified in each descriptive dimension; Based on the identified single measurement dimensions and control measurement dimension pairs, a pre-trained AI model is used to build an editable prospective enterprise questionnaire document for each enterprise; In response to at least one document editing process on the editable potential enterprise questionnaire document, a target potential enterprise questionnaire document is obtained; The target intended enterprise questionnaire document is rendered to obtain an electronic questionnaire of the intended enterprise for providing to job seekers to fill in online.

2. The method according to claim 1, characterized in that Mining and processing the relevant information of large-scale enterprises, and obtaining binary quantitative description values ​​of each enterprise under multiple preset description dimensions, including: Obtain a pre-built dimension table, wherein the dimension table includes multiple description dimensions, and a first quantitative description value and a second quantitative description value corresponding to each description dimension; According to the dimension table and the preset prompt word template, a set of information mining prompt words corresponding to each enterprise is constructed; Each information mining prompt word in each information mining prompt word set is used to mine the binary quantitative description value of the set enterprise under the set description dimension to be the first quantitative description value or the second quantitative description value corresponding to the description dimension; The large-scale enterprise-related information and information mining prompt word set of each enterprise are respectively input into the pre-trained large language model to obtain the quantitative description value of each enterprise in each description dimension.

3. The method according to claim 1, characterized in that Enterprises are grouped according to their binary quantitative description values ​​under each descriptive dimension, and based on the grouping results, single measurement dimensions and comparison measurement dimension pairs are identified in each descriptive dimension, including: According to the binary quantitative description value under each description dimension, the description dimension is divided into a single tendency dimension and a general tendency dimension; The enterprises are grouped according to the binary quantitative description values ​​under each monomer tendency dimension, and each monomer tendency dimension is clustered according to the grouping result to obtain at least one monomer dimension clustering cluster; Obtain at least one monomer tendency dimension in each monomer dimension cluster as a single measurement dimension; Enterprises are grouped according to the binary quantitative description values ​​under each general tendency dimension, and based on the grouping results, multiple comparison measurement dimension pairs with complementary enterprise relationships are obtained in each general tendency dimension.

4. The method according to claim 3, characterized in that Enterprises are grouped according to the binary quantitative description values ​​under each general tendency dimension, and based on the grouping results, multiple comparison measurement dimension pairs with complementary relationships between enterprises are obtained in each general tendency dimension, including: Identify the first quantitative description value and the second quantitative description value under each general tendency dimension as a positive quantitative description value and a negative quantitative description value; Obtain the positive enterprise groups under the positive quantitative description values ​​and the negative enterprise groups under the negative quantitative description values ​​for each general tendency dimension; If it is determined that the positive enterprise group of the first general tendency dimension and the negative enterprise group of the second general tendency dimension meet the preset difference condition, the first general tendency dimension and the second general tendency dimension are used as a comparison measurement dimension pair.

5. The method according to any one of claims 1 to 4, characterized in that: After mining and processing the relevant information of each large-scale enterprise to obtain the binary quantitative description value of each enterprise under multiple preset description dimensions, it also includes: Mining and processing the relevant information of large-scale enterprises to obtain detailed description information and scoring values ​​of each enterprise under multiple preset description dimensions; Accordingly, after obtaining the electronic questionnaire of the intended enterprise for the job seekers to fill out online, it also includes: In response to a request for filling out an intention questionnaire sent by a job-seeking client, an electronic questionnaire of the intended enterprise is provided to the job-seeking client for display so that the job-seeker can fill out the questionnaire online; Screening out a first number of predicted intended enterprises from each of the enterprises according to the online questionnaire filling results of the job-seeking client in response to the electronic questionnaire of the intended enterprises; Under each description dimension, a second number of target description dimensions are selected, and a multi-dimensional scoring chart of each forecast intention enterprise under each target description dimension is generated; Input the detailed description information of each predicted potential enterprise under each description dimension into the pre-trained large language model to obtain the comprehensive description information matching each predicted potential enterprise; The multi-dimensional scoring chart and comprehensive descriptive information corresponding to each predicted potential enterprise will be provided to the job-seeking client for display in separate items.

6. The method according to claim 5, characterized in that After providing the multi-dimensional scoring charts and comprehensive description information corresponding to each predicted intended enterprise to the job-seeking client for display, it also includes: In response to the enterprise comparison request sent by the job-seeking client, a list of enterprises consisting of predicted intended enterprises is provided to the job-seeking client for display; In response to the job-seeking client selecting multiple target predicted intended enterprises for comparison in the enterprise list; Based on the detailed description information of each target predicted intention enterprise under each description dimension, a multi-dimensional enterprise comparison table is constructed, and the multi-dimensional enterprise comparison table is provided to the job search client for display.

7. A device for generating an electronic questionnaire for potential enterprises, characterized in that: include: A quantitative description value acquisition module is used to collect large-scale enterprise-related information of various enterprises on multiple platforms, and mine and process the relevant information of each large-scale enterprise to obtain the binary quantitative description value of each enterprise under multiple preset description dimensions; A dimension identification module is used to group enterprises according to the binary quantitative description values ​​of each enterprise under each description dimension, and to identify a single measurement dimension and a comparison measurement dimension pair in each description dimension according to the grouping result; An editable questionnaire generation module is used to construct an editable prospective enterprise questionnaire document for each enterprise using a pre-trained artificial intelligence model based on the identified single measurement dimensions and control measurement dimension pairs; An editing response module, used for obtaining a target potential enterprise questionnaire document in response to at least one document editing process on the editable potential enterprise questionnaire document; The electronic questionnaire rendering module is used to render the target intended enterprise questionnaire document to obtain the intended enterprise electronic questionnaire for job seekers to fill out online.

8. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the method for generating an electronic questionnaire for potential enterprises according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the method for generating an electronic questionnaire for potential enterprises according to any one of claims 1 to 6 when executed.

10. A computer program product, characterized in that The computer program product comprises a computer program, which, when executed by a processor, implements the method for generating an electronic questionnaire for potential enterprises according to any one of claims 1 to 6.

Images