Data processing method and device, equipment, storage medium and program product

Abstract

The embodiment of the invention provides a data processing method and device, equipment, a storage medium and a program product, and relates to the technical field of artificial intelligence. The method comprises the steps of obtaining a data processing request, wherein the data processing request comprises resource allocation data of a target object and a first text; wherein the resource allocation data is used for indicating a current resource allocation result of the target object, and the first text is used for indicating a resource allocation requirement of the target object; performing structured processing on the first text to obtain structured information of the target object, the structured information of the target object including a first allocation condition corresponding to the resource allocation requirement; and determining the state of the resource allocation result according to the first allocation condition, wherein the state is a normal state or an abnormal state. According to the scheme, the efficiency of determining the state of the resource allocation result is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of artificial intelligence, and in particular to a data processing method and device, equipment, a storage medium and a program product. BACKGROUND

[0002] Resource allocation refers to allocating resources of a target object according to resource allocation requirements of the target object. In some scenarios, the resource allocation result in the resource allocation process is variable, and therefore, it is necessary to detect whether the resource allocation result in the resource allocation process is abnormal according to the resource allocation requirements of the target object.

[0003] In related technologies, the resource allocation requirements and resource allocation criteria of the target object can be analyzed in an artificial manner to determine the resource allocation conditions of the target object, so as to detect whether the resource allocation result is abnormal based on the resource allocation conditions. However, the above-mentioned manner has low efficiency in detecting whether the resource allocation result is abnormal. SUMMARY

[0004] Embodiments of the present application provide a data processing method, device, equipment, storage medium and program product to improve the efficiency of determining the state of the resource allocation result.

[0005] In a first aspect, the present application provides a data processing method, comprising:

[0006] obtaining a data processing request, wherein the data processing request comprises resource allocation data of a target object and a first text; the resource allocation data is used to indicate a current resource allocation result of the target object, and the first text is used to indicate resource allocation requirements of the target object;

[0007] structurally processing the first text to obtain structured information of the target object, wherein the structured information of the target object comprises a first allocation condition corresponding to the resource allocation requirements;

[0008] determining a state of the resource allocation result according to the first allocation condition, wherein the state is a normal state or an abnormal state.

[0009] In a second aspect, the present application provides a data processing device, comprising:

[0010] an obtaining module configured to obtain a data processing request, wherein the data processing request comprises resource allocation data of a target object and a first text; the resource allocation data is used to indicate a current resource allocation result of the target object, and the first text is used to indicate resource allocation requirements of the target object;

[0011] a processing module configured to structurally process the first text to obtain structured information of the target object, wherein the structured information of the target object comprises a first allocation condition corresponding to the resource allocation requirements; and

[0012] determining a state of the resource allocation result according to the first allocation condition, the state being a normal state or an abnormal state.

[0013] In a third aspect, the present application provides a data processing device, comprising:

[0014] at least one processor; and

[0015] a memory in communication connection with the at least one processor; wherein

[0016] 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 data processing method of the first aspect.

[0017] In a fourth aspect, the present application provides a computer readable storage medium, and the computer readable storage medium stores computer execution instructions, and the computer execution instructions are executed by a processor to implement the data processing method of the first aspect.

[0018] In a fifth aspect, the present application provides a computer program product, comprising a computer program, and the computer program is executed by a processor to implement the data processing method of the first aspect.

[0019] The data processing method provided by the present application, after the server receives the first text and the resource allocation result of the target object at the current time, the first text is structured and processed to obtain the first allocation condition represented by the structured statement, and then the state of the resource allocation result is determined based on the first allocation condition. In the above method, the first allocation condition is obtained by the server structuring and processing the first text, compared with the process of obtaining the first allocation condition by manually interpreting the first text, the efficiency of determining the first allocation condition is improved, and the efficiency of determining the state of the resource allocation result is improved. BRIEF DESCRIPTION OF DRAWINGS

[0020] The accompanying drawings, which are incorporated into and form part of the specification, illustrate embodiments consistent with the present application and, together with the specification, serve to explain the principles of the application.

[0021] Figure 1 A schematic diagram of an application scenario provided by an embodiment of the present application;

[0022] Figure 2 A flowchart of a data processing method provided by an embodiment of the present application;

[0023] Figure 3 A flowchart of determining the state of the resource allocation result provided by an embodiment of the present application;

[0024] Figure 4 A data processing process schematic diagram provided for an embodiment of the present application;

[0025] Figure 5 A process schematic diagram for determining the state of the resource allocation result provided for an embodiment of the present application;

[0026] Figure 6 A process schematic diagram for predicting the state of the resource allocation result provided for an embodiment of the present application;

[0027] Figure 7 A structure schematic diagram of a data processing device provided for an embodiment of the present application;

[0028] Figure 8 A structure schematic diagram of a data processing device provided for an embodiment of the present application.

[0029] The specific embodiments of the present application have been shown through the above-described drawings, and will be described in more detail hereinafter. These drawings and textual descriptions are not intended to limit the scope of the concept of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0030] The exemplary embodiments will be described in detail herein with reference to the attached drawings. The following description is made with reference to the accompanying drawings in which like reference numerals refer to like elements, unless otherwise indicated. The following exemplary embodiments described in the following description are not meant to be limiting of the present application. Instead, they are meant to provide examples of apparatus and methods in accordance with aspects of the present application as detailed in the appended claims.

[0031] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present application are all information and data authorized by the user or authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of the relevant data comply with the relevant laws, regulations and standards of the relevant countries and regions, necessary security measures are taken, public order and good customs are not violated, and appropriate operation portals are provided for the user to choose authorization or refusal.

[0032] And the present application relates to the user information for big data analysis (including but not limited to personal biological characteristics, identity data, consumption data, asset data, electronic terminal operation data, etc.), and adopts artificial intelligence technology to make automatic decision, based on the automatic decision result makes the technical scheme of the decision of the personal rights and interests has the important influence, provides the corresponding operation entrance for user, for user to choose to agree or refuse the automatic decision result;If the user chooses to refuse, enter the expert decision process.

[0033] It should be noted that the data processing method, apparatus, device, storage medium and program product provided by the present application can be used in the field of artificial intelligence technology, and can also be used in any field other than the field of artificial intelligence technology. The application field of the data processing method, apparatus, device, storage medium and program product in the present application is not limited.

[0034] Resource hosting is a process of authorizing user resources to a platform for custody and distribution. The core of resource hosting is to ensure the security of user resources and that the resource hosting process complies with relevant specifications. The relevant specifications can be indicated by specification texts. In some embodiments, resource hosting can also be referred to as resource distribution.

[0035] In some scenarios, the resource allocation result in the process of resource allocation to the target object is changing, therefore, it is necessary to detect the resource allocation result of the target object in real time to determine the state of the resource allocation result. In the case that the state of the resource allocation result is abnormal, the resource allocation result of the target object is adjusted in time, so that the state of the resource allocation result is normal.

[0036] In the related art, the first text and the second text can be interpreted by artificial means to determine the resource allocation requirements and resource allocation criteria of the target object. Then the resource allocation conditions and resource allocation criteria are converted into resource allocation conditions represented by structured statements based on the rule base. The server determines the state of the resource allocation result of the target object based on the resource allocation conditions.

[0037] With the explosive growth of resource allocation demand, it is necessary to detect whether the resource allocation result of a large number of target objects is abnormal. Therefore, a large number of resource allocation conditions need to be determined, and a large number of resource allocation conditions need to be converted into structured information. However, the efficiency of manually determining resource allocation conditions and converting resource allocation conditions into structured information is low, resulting in low efficiency of determining the state of the resource allocation result.

[0038] Based on this, the embodiment of the application provides a data processing method. After receiving a data processing request, a server performs structured processing on a first text to generate a first allocation condition represented by a structured statement. Compared with a manner of manually determining the first allocation condition, the data processing method provided by the application improves the efficiency of determining the first allocation condition, and further improves the efficiency of determining the state of the resource allocation result.

[0039] For ease of understanding, the following will be combined with Figure 1 The application scenario to which the embodiment of the application is applied will be briefly described.

[0040] Figure 1 A schematic diagram of an application scenario provided by the embodiment of the application is shown in FIG. 1. Figure 1 , comprising a first device 11 and a server 12, wherein the data processing system is deployed in the first device 11, and the first device 11 is a client of the data processing system, and the server 12 is a background server of the data processing system.

[0041] In actual application, the first device 11 and the server 12 can communicate with each other. For example, the first device 11 can send a data processing request to the server 12, and the server 12 can send a prompt information to the first device 11.

[0042] It should be noted that Figure 1 is only an exemplary form of a schematic application scenario, and is not a limitation on the application scenario.

[0043] The technical solution of the application and how the technical solution of the application solves the above technical problems will be described in detail in the following specific embodiments. The following several specific embodiments can be combined with each other, and the same or similar concepts or processes can not be described in some embodiments. The embodiments of the application will be described below with reference to the drawings.

[0044] Figure 2 A flowchart of a data processing method provided by the embodiment of the application is shown in FIG. 2. Figure 2 The method can include the following steps:

[0045] S21, obtaining a data processing request, wherein the data processing request includes resource allocation data of a target object and a first text; wherein the resource allocation data is used to indicate the current resource allocation result of the target object, and the first text is used to indicate the resource allocation requirement of the target object.

[0046] The execution subject of the embodiment of the application can be a server, or a data processing device arranged in the server. The data processing device can be realized by software, or realized by the combination of software and hardware.

[0047] The target object refers to a subject of resource allocation. The target object can be a specific physical object or an abstract resource. For example, the target object can be time, data, user resources, etc.

[0048] In some embodiments, resource allocation is required for the target object. It should be noted that the process of allocating resources to the target object involves at least one allocation type. First, the resources allocated to each allocation type are determined according to the resource allocation requirements. The resources allocated to each allocation type can be the resource allocation result. Specifically, the resource allocation result of the target object can be determined by analyzing the resource allocation requirements indicated by the first text.

[0049] For example, taking the target object as user resources and the resource allocation of the target object as resource hosting of user resources as an example, the first text can be, for example, a specification text of user resources, which is used to indicate the hosting requirements when the user resources are hosted. Assuming that the user resources are 1000 units, the at least one allocation type can include an equity allocation type and a collection management allocation type, and the resource allocation requirements can include, for example, that the resource allocation proportion of each equity allocation type is not more than 30% of the user resources, and the resource allocation proportion of each collection management allocation type is not less than 20% of the user resources. It can be determined that the resource allocation result includes 200 units of resources allocated to the equity allocation type and 800 units of resources allocated to the collection management allocation type.

[0050] Taking the target object as memory resources as an example, the first text can be, for example, an allocation specification text of memory resources. Assuming that the memory resources are 1024 MB, the at least one allocation type includes an execution computing task type and a system application loading type. The resource allocation requirements can include, for example, that the resources allocated to the execution computing task type are not less than 40% of the memory resources, and the resources allocated to the system application loading type are not more than 30% of the memory resources. It can be determined that the resource allocation result includes 512 MB of resources allocated to the execution computing task type and 256 MB of resources allocated to the system application loading type.

[0051] In some embodiments, after the target object is allocated resources, the resource allocation result of the target object will change. Therefore, it is necessary to detect in real time whether the resource allocation result meets the resource allocation requirements of the target object.

[0052] S22, structurally processing the first text to obtain structured information of the target object, the structured information of the target object including a first allocation condition corresponding to the resource allocation requirements.

[0053] In some embodiments, the first text is expressed in a natural language. After receiving the data processing request, the server can perform a structured processing on the first text to obtain structured information expressed in a structured statement. The structured processing on the first text refers to converting the resource allocation result indicated by the first text into the first allocation condition expressed in a structured statement. The structured statement can be, for example, a structured query language (SQL) statement. Since the structured information obtained after the structured processing on the first text is expressed in a structured statement, and the structured information includes the first allocation condition, the first allocation condition is also expressed in a structured statement.

[0054] The first allocation condition refers to a constraint condition for resource allocation of the target object. The first allocation condition can include a condition that the resource allocated for at least one allocation type meets, and a condition that an evaluation index for resource allocation of the target object meets. In a resource hosting scenario, the evaluation index for resource allocation of the target object can include a first index and a second index. The first index is used to measure the robustness of the user resource in the resource hosting process. For each allocation type in the at least one allocation type, the larger the first index of the allocation type, the weaker the robustness of the resource allocated for the allocation type; the smaller the first index of the allocation type, the stronger the robustness of the resource allocated for the allocation type. The second index is used to measure the health degree of the user resource in the resource hosting process. For each allocation type in the at least one allocation type, the larger the second index of the allocation type, the higher the health degree of the resource allocated for the allocation type; the smaller the second index of the allocation type, the lower the health degree of the resource allocated for the allocation type. The first index and the second index can be expressed in the form of a percentage.

[0055] For example, taking the target object as a user resource, the resource allocation of the target object as the resource hosting of the user resource, and assuming that the at least one allocation type includes an equity allocation type and a collective management allocation type, and the evaluation index for resource allocation of the target object includes a first index and a second index. The condition that the resource allocated for at least one allocation type meets can include: the resource allocation proportion of the equity allocation type <= 30% of the user resource, and the resource allocation proportion of the collective management allocation type >= 20% of the user resource; and the condition that the evaluation index for resource allocation of the target object meets can include: the first index of the equity allocation type <= 20%, the second index of the equity allocation type >= 120%, the first index of the collective management allocation type <= 30%, and the second index of the collective management allocation type >= 100%.

[0056] In some embodiments, the first allocation condition is represented by a structured statement. For example, assuming that the first allocation condition is that the first metric of the equity allocation type is less than or equal to 20%, the first allocation condition is represented by a structured statement as follows: SELECT * FROM equity allocation WHERE allocation type = 'equity' AND first metric percent <= 20.

[0057] S23, determining a state of the resource allocation result according to the first allocation condition, the state being a normal state or an abnormal state.

[0058] In some embodiments, whether the resource allocation result meets the resource allocation requirement of the target object can be determined by determining the state of the resource allocation result. Specifically, when the state of the resource allocation result is the normal state, it is determined that the resource allocation result meets the resource allocation requirement of the target object; when the state of the resource allocation result is the abnormal state, it is determined that the resource allocation result does not meet the resource allocation requirement of the target object.

[0059] In some embodiments, the state of the resource allocation result can be determined by determining whether the resource allocation result meets the first allocation condition. When the resource allocation result meets the first allocation condition, the state of the resource allocation result is determined to be the normal state; when the resource allocation result does not meet the first allocation condition, the state of the resource allocation result is determined to be the abnormal state.

[0060] For example, assuming that the target object is a user resource, the resource allocation to the target object is the resource hosting of the user resource, and the first allocation condition is "SELECT * FROM equity allocation WHERE allocation type = 'equity' AND first metric percent >= 40". If the first metric of the equity allocation type in the resource allocation result is 30%, it is determined that the resource allocation result does not meet the first allocation condition. Therefore, the state of the resource allocation result is determined to be the abnormal state.

[0061] In Figure 2 In the embodiment shown in the figure, after receiving the data processing request, the server performs structured processing on the first text to generate the first allocation condition corresponding to the resource allocation requirement, and the first allocation condition is represented by a structured statement. Compared with the way of manually determining the first allocation condition, Figure 2 The data processing method shown in the figure improves the efficiency of determining the first allocation condition. Then, the server determines the state of the resource allocation result according to the first allocation condition to be the normal state or the abnormal state. Since Figure 2The data processing method shown improves the efficiency of determining the first allocation condition, and thus Figure 2 The data processing method shown also improves the efficiency of determining the state of the resource allocation result.

[0062] In Figure 2 Based on the embodiments shown, the following will be combined Figure 3 Further description will be made on the implementation manner of determining the state of the resource allocation result according to the first allocation condition.

[0063] Figure 3 A flowchart for determining the state of the resource allocation result is provided for the embodiments of the present application. Please refer to Figure 3 The process can include the following steps:

[0064] S31, acquire a third text, the third text is used to indicate resource allocation criteria of at least one object, and the at least one object includes a target object.

[0065] The third text refers to a normative document for allocating resources to at least one object. It should be noted that the third text is expressed in natural language. In some embodiments, the third text can be obtained by scanning, crawling, etc.

[0066] The resource allocation criteria are used to indicate the rules and standards for allocating resources to each object in the at least one object. In some embodiments, during the process of allocating resources to the at least one object, the resource allocation result of each object of the at least one object needs to meet the resource allocation criteria. Since the at least one object includes the target object, the current resource allocation result of the target object also needs to meet the resource allocation criteria during the allocation process of the target object.

[0067] S32, structurally process the third text to obtain structured information of the at least one object, and the structured information of the at least one object includes a second allocation condition corresponding to the resource allocation criteria.

[0068] Since the third text is expressed in natural language, after the server acquires the third text, it can structurally process the third text to convert the resource allocation criteria indicated by the third text into a second allocation condition expressed in a structured statement.

[0069] Specifically, the manner of determining the structured information of the at least one object can be as follows: acquire a fourth text, the fourth text includes a question of structurally processing the third text to the large model and a second prompt word; input the third text and the fourth text into the large model to obtain the structured information of the at least one object.

[0070] The fourth text refers to an instructive text input to the large model. The question of structuring the third text proposed to the large model refers to the processing requirements of the third text. For example, the question of structuring the third text proposed to the large model can be: "Analyze the resource allocation criteria in the third text and convert the resource allocation criteria into structured information, requiring conditions such as allocation proportion, time limit, priority, etc." The large model can be, for example, an Artificial Intelligence Generated Content (AIGC) large model, etc.

[0071] The second prompt word refers to guiding keywords, constraint conditions, etc. when processing the third text. The second prompt word can specify, for example, the type of structured statement, key indicators in the third text, constraint logic relationships, etc.

[0072] For example, assuming the third text is "R&D resources are allocated to projects with progress exceeding 60%, and each project does not exceed 30% of the total budget", the second prompt word can include: the output format is structured statement format, determine the input proportion limit, etc.

[0073] The large model processes the third text according to the question of structuring the third text and the second prompt word, and obtains structured information of at least one object.

[0074] S33, determine the state of the resource allocation result according to the first allocation condition and the second allocation condition.

[0075] The first allocation condition is obtained based on the resource allocation requirements of the target object, and the second allocation condition is obtained based on the resource allocation criteria of at least one object. In the process of allocating resources to the target object, the resource allocation result of the target object needs to meet the first allocation condition and the second allocation condition.

[0076] Therefore, the way to determine the state of the resource allocation result can be as follows: update the first allocation condition according to the second allocation condition to obtain a third allocation condition; in the case where the resource allocation result meets the third allocation condition, determine that the state of the resource allocation result is a normal state; in the case where the resource allocation result does not meet the third allocation condition, determine that the state of the resource allocation result is an abnormal state.

[0077] In some embodiments, the first allocation condition comprises a first field and a first range corresponding to the first field; the second allocation condition comprises the first field and a second range corresponding to the first field, and / or a second field and a third range corresponding to the second field. The manner of updating the first allocation condition according to the second allocation condition to obtain the third allocation condition can be as follows: in the case where the second allocation condition comprises the first field and the second range corresponding to the first field, determining a target range corresponding to the first field according to the first range and the second range; the third allocation condition comprises the first field and the target range corresponding to the first field; in the case where the second allocation condition comprises the second field and the third range corresponding to the second field, determining that the third allocation condition comprises the second field and the third range corresponding to the second field.

[0078] The first field is used to indicate a specific object subject to the regulation or constraint of the first allocation condition, and the first range corresponding to the first field is used to indicate the limit range of the first field in the first allocation condition. For example, assuming that the first allocation condition is that the first index <= 20%, the first field in the first allocation condition is "first index", and the first range corresponding to the first field is "less than or equal to 20%".

[0079] In some embodiments, the second allocation condition can also comprise the first field, and the limit range of the first field in the second allocation condition is the second range. It should be noted that the second range can be the same as or different from the first range. In some embodiments, the second allocation condition can also comprise the second field, and the limit range of the second field in the second allocation condition is the third range.

[0080] In the case where the second allocation condition comprises the first field and the second range corresponding to the first field, a subset of the first range and the second range can be determined as the target range corresponding to the first field.

[0081] For example, assuming that the first allocation condition comprises the first index <= 20%, and the second allocation condition comprises the first index <= 30% and the second index >= 100%, it is determined that the third allocation condition comprises: the first field is "first index", the first range corresponding to the first field is "less than or equal to 20%", the second range corresponding to the first field is "less than or equal to 30%", the second field is "second index", and the third range corresponding to the second field is "greater than or equal to 100%". According to the subset of the first range and the second range, the target range corresponding to the first field is determined to be "less than or equal to 20%". At this time, it is determined that the third allocation condition comprises the first index <= 20% and the second index >= 100%.

[0082] Exemplarily, taking the target object as a user resource, the target object as a resource allocation, and the resource allocation as a resource hosting of the user resource as an example, it is assumed that the user resource is 1000 units, and at least one allocation type can include an equity type allocation type and a collective management type allocation type.

[0083] The third allocation condition includes that the resource allocation proportion of the equity type allocation type <= 30% of the user resource, the resource allocation proportion of the collective management type allocation type >= 20% of the user resource, the first index of the equity type allocation type <= 20%, the second index of the equity type allocation type >= 120%, the first index of the collective management type allocation type <= 30%, and the second index of the collective management type allocation type >= 100%.

[0084] The resource allocation result includes that the resource allocated for the equity type allocation type is 200 units, the resource allocated for the collective management type allocation type is 800 units, the first index of the equity type allocation type is 30%, the second index of the equity type allocation type is 130%, the first index of the collective management type allocation type is 20%, and the second index of the collective management type allocation type is 90%.

[0085] Since the first index of the equity type allocation type is greater than 20% and the second index of the collective management type allocation type is less than 100% in the resource allocation result, it is determined that the resource allocation result does not satisfy the third allocation condition, that is, the state of the resource allocation result is an abnormal state.

[0086] In some embodiments, in the case where the state of the resource allocation result is an abnormal state, the server can send prompt information to the client, and the prompt information is used to prompt that the state of the resource allocation result is an abnormal state.

[0087] In Figure 3 In the embodiment shown, the server performs structural processing on the third text to obtain the second allocation condition of the at least one object. Compared with the manner of manually processing the third text to obtain the at least one second allocation condition, the data processing method provided in the present application improves the efficiency of determining the second allocation condition, thereby further improving the efficiency of determining the state of the resource allocation result. In addition, since the first allocation condition is obtained by performing structural processing on the first text, and the second allocation condition is obtained by performing structural processing on the third text, compared with the manner of manually determining the first allocation condition and the second allocation condition, which may have the problem of misreading or missing reading, the data processing method provided in the present application performs structural processing on the first text and the second text respectively to obtain the first allocation condition and the second allocation condition, which improves the accuracy of determining the first allocation condition and the second allocation condition, and further improves the accuracy of determining the state of the resource allocation result when the state of the resource allocation result is determined according to the first allocation condition and the second allocation condition.

[0088] On the basis of the above-mentioned embodiments, below, combined with Figure 4 The data processing method provided by the embodiments of the application is further described.

[0089] Figure 4 A data processing process diagram is provided for the embodiments of the application. As Figure 4 shown, after inputting the first text into the server 12, the server 12 performs structured processing on the first text through the large model to obtain the first allocation condition, and determines the state of the resource allocation result according to the first allocation condition.

[0090] Specifically, the process can be understood in combination with Figure 5 Figure 5 A process diagram for determining the state of the resource allocation result is provided for the embodiments of the application. As Figure 5 shown, after receiving the first text, the server obtains the second text, which includes a question to the large model for structured processing of the first text and a first prompt word; the first text and the second text are input into the large model to obtain structured information.

[0091] Among them, the second text refers to the instructive text input to the large model. The question to the large model for structured processing of the first text refers to the processing requirement of the first text. For example, the question to the large model for structured processing of the first text can be: "analyze the resource allocation requirement in the first text, and convert the resource allocation requirement into structured information, requiring to include allocation proportion, time limit, priority, etc." The second prompt word refers to the guiding key word, constraint condition, etc. for processing the first text.

[0092] Specifically, the server can include functional modules such as an input module, an analysis module and an output module, wherein the input module is to input the first text into the large model. In some embodiments, the input module can also input a rule table to the large model. The rule table is used to indicate the association relationship between natural language and structured language, so that the large model can convert the resource allocation requirement into the first allocation condition according to the rule table.

[0093] The analysis module obtains the second text and inputs the second text into the large model, and the second text includes a question to the large model for structured processing of the first text and a first prompt word. The large model can analyze the first text according to the question to the large model for structured processing of the first text, the first prompt word, determine the resource allocation requirement indicated in the first text, and convert the resource allocation requirement into target object structured information, so as to obtain the first allocation condition of the target object, and then output the first allocation condition through the output module.

[0094] ​Exemplarily, the large model can perform semantic analysis on the first text, determine the resource allocation condition indicated in the first text, and convert the resource allocation requirement into structured information through a natural language to structured query language (NL2SQL) technology.

[0095] In some embodiments, the large model can also generate a mapping relationship between the resource allocation requirement and the first allocation condition, thereby facilitating the staff to query the resource allocation requirement corresponding to the first allocation condition.

[0096] In some embodiments, the resource allocation result also needs to meet at least one resource allocation criterion of an object. Therefore, the input module can also input the third text to the large model, the parsing module obtains the fourth text, and inputs the fourth text to the large model. The large model analyzes the third text according to the question of structuring the third text proposed to the large model, the second prompt word, determines the resource allocation criterion indicated in the third text, and converts the resource allocation criterion into structured information of at least one object, thereby obtaining a second allocation condition of at least one object, and then outputs the second allocation condition through the output module.

[0097] In some embodiments, the large model can also generate a mapping relationship between the resource allocation criterion and the second allocation condition, thereby facilitating the staff to query the resource allocation criterion corresponding to the second allocation condition.

[0098] Then, the server updates the first allocation condition according to the second allocation condition, and determines the state of the resource allocation result according to the obtained third allocation condition.

[0099] In some embodiments, the server 12 can also generate an abnormal report of the resource state result in the case that the state of the resource allocation result is an abnormal state, and obtain dynamic information corresponding to each of the at least one allocation type. Then, according to the abnormal report and / or the dynamic information corresponding to each of the at least one allocation type, a state prediction report of the target object is generated, which is used to indicate the resource prediction result of the target object after the current time.

[0100] It can be combined with Figure 6 understand this process, Figure 6 a process for predicting the state of the resource allocation result provided by the embodiments of the present application. As Figure 6 shown, the server determines the state of the resource allocation result according to the first allocation condition after obtaining the data processing request. And in the case that the state of the resource allocation result is an abnormal state, an abnormal report of the resource allocation result is generated. Among them, the abnormal report includes at least one allocation condition that does not meet the resource allocation requirement, and / or the resource allocation criterion.

[0101] In some embodiments, the server can further obtain a plurality of dynamic information, and determine at least one dynamic information corresponding to each of the allocation types in the plurality of dynamic information. The dynamic information can be, for example, feedback information corresponding to the allocation types, etc. Then, the server inputs the abnormal report of the resource allocation result and / or the at least one dynamic information corresponding to each of the allocation types into the large model. It should be noted that the server can further input a third prompt word into the large model, and the server can further input a question to the large model for predicting the abnormal report of the resource allocation result and / or the at least one dynamic information corresponding to each of the allocation types. The third prompt word is used to indicate the guiding keywords, constraints, etc. when predicting the abnormal report of the resource allocation result and / or the at least one dynamic information corresponding to each of the allocation types.

[0102] The large model predicts the abnormal report of the resource allocation result and / or the at least one dynamic information corresponding to each of the allocation types according to the third prompt word and the question to the large model for predicting the abnormal report of the resource allocation result and / or the at least one dynamic information corresponding to each of the allocation types, and generates a state prediction report of the target object.

[0103] In some embodiments, after generating the state prediction report, the server can send the state prediction report to the client through an email or the like.

[0104] In Figure 4 In the embodiment shown, after determining the state of the resource allocation result, the server determines a state prediction report of a resource prediction result of the target object after the current time according to the abnormal report of the resource allocation result and the dynamic information corresponding to each of the allocation types. In the above method, the state prediction report is determined in combination with data of different dimensions, which improves the accuracy of determining the state prediction report. In addition, by generating the state prediction report, the "post-event prompt" is converted into "pre-event prediction", and the server can timely adjust the resource allocation of the target object through the state prediction report, thereby reducing the probability that the state of the resource allocation result is an abnormal state.

[0105] Figure 7 A structural schematic diagram of a data processing apparatus provided by an embodiment of the present application is shown in FIG. 7. Please refer to FIG. 7, Figure 7 The data processing apparatus 70 provided by the embodiment of the present application includes an acquisition module 71, a processing module 72 and a determination module 73, wherein,

[0106] The acquisition module 71 is configured to acquire a data processing request, wherein the data processing request includes resource allocation data of a target object and a first text. The resource allocation data is used to indicate a current resource allocation result of the target object, and the first text is used to indicate a resource allocation requirement of the target object.

[0107] The processing module 72 is configured to perform structural processing on the first text to obtain structural information of the target object, the structural information of the target object including a first allocation condition corresponding to the resource allocation requirement.

[0108] The determining module 73 is configured to determine a state of the resource allocation result according to the first allocation condition, the state being a normal state or an abnormal state.

[0109] In a possible implementation, the processing module 72 is specifically configured to:

[0110] obtain a second text, the second text including a question of performing structural processing on the first text and a first prompt word for the large model;

[0111] input the first text and the second text into the large model to obtain the structural information.

[0112] In a possible implementation, the determining module 73 is specifically configured to:

[0113] obtain a third text, the third text being used to indicate a resource allocation criterion of at least one object, the at least one object including the target object;

[0114] perform structural processing on the third text to obtain structural information of the at least one object, the structural information of the at least one object including a second allocation condition corresponding to the resource allocation criterion;

[0115] determine the state of the resource allocation result according to the first allocation condition and the second allocation condition.

[0116] In a possible implementation, the determining module 73 is specifically configured to:

[0117] obtain a fourth text, the fourth text including a question of performing structural processing on the third text and a second prompt word for the large model;

[0118] input the third text and the fourth text into the large model to obtain the structural information of the at least one object.

[0119] In a possible implementation, the determining module 73 is specifically configured to:

[0120] update the first allocation condition according to the second allocation condition to obtain a third allocation condition;

[0121] in a case where the resource allocation result satisfies the third allocation condition, determine that the state of the resource allocation result is the normal state;

[0122] in a case where the resource allocation result does not satisfy the third allocation condition, determine that the state of the resource allocation result is the abnormal state.

[0123] In a possible implementation, the first allocation condition includes a first field and a first range corresponding to the first field, and the second allocation condition includes the first field and a second range corresponding to the first field, and / or a second field and a third range corresponding to the second field. The determining module 73 is specifically configured to:

[0124] In a case where the second allocation condition includes the first field and the second range corresponding to the first field, the target range corresponding to the first field is determined according to the first range and the second range. The third allocation condition includes the first field and the target range corresponding to the first field.

[0125] In a case where the second allocation condition includes the second field and the third range corresponding to the second field, it is determined that the third allocation condition includes the second field and the third range corresponding to the second field.

[0126] In a possible implementation, the determining module 73 is specifically configured to:

[0127] The first range and a subset of the second range are determined as the target range corresponding to the first field.

[0128] In a possible implementation, in a case where the state of the resource allocation result is the abnormal state, the data processing apparatus 70 further includes a sending module. The sending module is specifically configured to:

[0129] Send prompt information to the client. The prompt information is used to prompt that the state of the resource allocation result is the abnormal state.

[0130] The data processing apparatus 70 provided by the embodiments of the present application can execute the technical solutions in the above embodiments, and the implementation principles and beneficial effects are similar, which will not be repeated here.

[0131] Figure 8 A structural schematic diagram of a data processing device provided by an embodiment of the present application is shown in FIG. 8. As shown in the figure, the data processing device 80 can include a memory 81 and at least one processor 82. Exemplarily, the memory 81 and the at least one processor 82 are connected with each other through a bus 83. Figure 8

[0132] The memory 81 is used to store program instructions.

[0133] The at least one processor 82 is used to execute the program instructions stored in the memory, so as to enable the data processing device 80 to execute the data processing method in the above method embodiments.

[0134] ​Optionally, the processor can be a central processing unit (CPU), and can also be a graphics processing unit (GPU), other general purpose processors, a digital signal processor (DSP), an application specific integrated circuit (ASIC), or the like. The general purpose processor can be a microprocessor or the like. The steps of the method disclosed in combination with the embodiments of the present application can be directly embodied as a hardware processor for execution, or a combination of hardware and software modules in the processor for execution.

[0135] The data processing device 80 provided by the embodiments of the present application can execute the data processing method in the method embodiments, and the implementation principles and advantages are similar, which will not be repeated here.

[0136] The embodiments of the present application provide a computer readable storage medium, wherein the computer readable storage medium stores computer execution instructions, and the computer execution instructions are executed by a processor to implement the data processing method in the method embodiments.

[0137] The embodiments of the present application provide a computer program product, comprising a computer program, which is executed by a processor to implement the data processing method in the method embodiments.

[0138] The embodiments of the present application provide a chip, and the chip stores a computer program, and the computer program is executed by the chip to implement the data processing method in the method embodiments.

[0139] The embodiments of the present application provide a chip module, and the chip module stores a computer program, and the computer program is executed by the chip module to implement the data processing method in the method embodiments.

[0140] It should be noted that, for the foregoing method embodiments, in order to simply describe, they are all described as a combination of a series of actions, but those skilled in the art should know that the present application is not limited to the order of the actions described, because according to the present application, certain steps can be performed in other order or simultaneously. Secondly, those skilled in the art should know that the embodiments described in the specification all belong to optional embodiments, and the actions and modules involved are not necessarily required by the present application.

[0141] It should be understood that the device embodiments described above are merely illustrative, and the device of the present application can also be implemented in other manners. For example, the division of the units / modules in the above embodiments is merely a logical function division, and the actual implementation can be in another manner. For example, two or more units / modules can be combined, or some features can be ignored or not executed.

[0142] It should be understood that the device embodiments described above are merely illustrative, and the device of the present application can also be implemented in other manners. For example, the division of the units / modules in the above embodiments is merely a logical function division, and the actual implementation can be in another manner. For example, two or more units / modules can be combined, or some features can be ignored or not executed.

[0143] In addition, unless specifically stated otherwise, each functional unit / module in each embodiment of the present application can be integrated in one unit / module, or each unit / module can exist physically, or two or more units / modules can be integrated together. The integrated unit / module can be implemented in the form of hardware or in the form of a software program module.

[0144] The integrated unit / module, if implemented in the form of hardware, can be a digital circuit, an analog circuit, etc. The physical implementation of the hardware structure includes but is not limited to transistors, memristors, etc. Unless specifically stated otherwise, the processor can be any appropriate hardware processor, such as a CPU, a GPU, a field programmable gate array (FPGA), a DSP, and an ASIC, etc. Unless specifically stated otherwise, the storage unit can be any appropriate magnetic storage medium or magneto-optical storage medium, such as a resistive random access memory (RRAM), a dynamic random access memory (DRAM), a static random access memory (SRAM), an enhanced dynamic random access memory (EDRAM), a high-bandwidth memory (HBM), a hybrid memory cube (HMC), etc.

[0145] If the integrated units / modules are implemented in the form of software program modules and sold or used as independent products, they can be stored in a computer readable memory. Based on such understanding, the technical solutions of the present application essentially or the part that contributes to the prior art or the whole or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a memory and includes a number of instructions for causing a computer device (which can be a personal computer, a server or a network device, etc.) to execute all or part of the steps of the embodiments of the method of the present application. The aforementioned memory includes: a U disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a mobile hard disk, a magnetic disk or an optical disk, and various media that can store program codes.

[0146] In the above embodiments, the description of each embodiment has its own focus, and the parts not described in detail in a certain embodiment can be referred to the related description of other embodiments. The technical features of the above embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the technical features in the above embodiments are described, however, as long as the combinations of the technical features do not exist contradictory, they should be considered as the scope of the present application.

[0147] Other embodiments of the application will be apparent to those skilled in the art from consideration of the specification and practice of the application disclosed herein. The application is intended to cover any variations, uses or adaptations of the application following, in general, the principles of the application and including such departures from the present disclosure as come within known or customary practice in the art to which the application pertains or can relate. The specification and examples are to be regarded as exemplary only, and the true scope and spirit of the application are indicated by the following claims.

[0148] It should be understood that the application is not limited to the precise construction that has been described and illustrated herein and that various modifications and changes can be made therein without departing from the scope thereof. The scope of the application is indicated by the appended claims rather than by the description.

Claims

1. A data processing method, characterized by, The method comprises: obtaining a data processing request, wherein the data processing request comprises resource allocation data of a target object and a first text; the resource allocation data is used to indicate a current resource allocation result of the target object, and the first text is used to indicate a resource allocation requirement of the target object; performing structured processing on the first text to obtain structured information of the target object, wherein the structured information of the target object comprises a first allocation condition corresponding to the resource allocation requirement; determining a state of the resource allocation result according to the first allocation condition, wherein the state is a normal state or an abnormal state.

2. The method of claim 1, wherein, The structured processing on the first text to obtain the structured information of the target object comprises: obtaining a second text, wherein the second text comprises a question of performing structured processing on the first text and a first prompt word; inputting the first text and the second text into the large model to obtain the structured information.

3. The method according to claim 1 or 2, characterized in that, The determination of the state of the resource allocation result according to the first allocation condition comprises: obtaining a third text, wherein the third text is used to indicate resource allocation criteria of at least one object, and the at least one object comprises the target object; performing structured processing on the third text to obtain structured information of the at least one object, wherein the structured information of the at least one object comprises a second allocation condition corresponding to the resource allocation criteria; determining the state of the resource allocation result according to the first allocation condition and the second allocation condition.

4. The method of claim 3, wherein, The structured processing on the third text to obtain the structured information of the at least one object comprises: obtaining a fourth text, wherein the fourth text comprises a question of performing structured processing on the third text and a second prompt word; inputting the third text and the fourth text into the large model to obtain the structured information of the at least one object.

5. The method of claim 3, wherein, The determination of the state of the resource allocation result according to the first allocation condition and the second allocation condition comprises: updating the first allocation condition according to the second allocation condition to obtain a third allocation condition; in a case where the resource allocation result satisfies the third allocation condition, determining that the state of the resource allocation result is the normal state; in a case where the resource allocation result does not satisfy the third allocation condition, determining that the state of the resource allocation result is the abnormal state.

6. The method of claim 5, wherein, The first allocation condition comprises a first field and a first range corresponding to the first field; the second allocation condition comprises the first field and a second range corresponding to the first field, and / or a second field and a third range corresponding to the second field; The updating of the first allocation condition according to the second allocation condition to obtain a third allocation condition comprises: in a case where the second allocation condition comprises the first field and the second range corresponding to the first field, determining a target range corresponding to the first field according to the first range and the second range; and the third allocation condition comprises the first field and the target range corresponding to the first field. In a case where the second allocation condition includes the second field and a third range corresponding to the second field, it is determined that the third allocation condition includes the second field and the third range corresponding to the second field.

7. The method of claim 6, wherein, The determining the target range corresponding to the first field according to the first range and the second range comprises: determining a subset of the first range and the second range as the target range corresponding to the first field.

8. The method of claim 1, wherein, In a case where the state of the resource allocation result is the abnormal state, the method further comprises: sending prompt information to the client, the prompt information being used to prompt that the state of the resource allocation result is the abnormal state.

9. A data processing apparatus, characterized by, The apparatus comprises: an obtaining module, configured to obtain a data processing request, the data processing request comprising resource allocation data of a target object and a first text; wherein the resource allocation data is used to indicate a current resource allocation result of the target object, and the first text is used to indicate a resource allocation requirement of the target object; a processing module, configured to perform structural processing on the first text to obtain structural information of the target object, the structural information of the target object comprising a first allocation condition corresponding to the resource allocation requirement; a determining module, configured to determine a state of the resource allocation result according to the first allocation condition, the state being a normal state or an abnormal state.

10. A data processing device, characterized by comprise: 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 cause the at least one processor to perform the data processing method in any one of claims 1 to 8.

11. A computer readable storage medium, characterized in that, The computer readable storage medium stores computer execution instructions, and the computer execution instructions are executed by the processor to implement the data processing method in any one of claims 1 to 8.

12. A computer program product, characterised in that, The computer program is executed by the processor to implement the data processing method in any one of claims 1 to 8.

Images